ERROR : error code -9

[zafersn]

Hi
DIGITS is crashing and leaving me with this error in the first couple of seconds of trying to build a new GoogleNet

ERROR: error code -9

I0314 22:54:40.272929 3497 net.cpp:200] val-data does not need backward computation.
I0314 22:54:40.272939 3497 net.cpp:242] This network produces output accuracy
I0314 22:54:40.272953 3497 net.cpp:242] This network produces output loss
I0314 22:54:40.272965 3497 net.cpp:242] This network produces output loss1/accuracy
I0314 22:54:40.272979 3497 net.cpp:242] This network produces output loss1/loss
I0314 22:54:40.272989 3497 net.cpp:242] This network produces output loss2/accuracy
I0314 22:54:40.273002 3497 net.cpp:242] This network produces output loss2/loss
I0314 22:54:40.273347 3497 net.cpp:255] Network initialization done.
I0314 22:54:40.275010 3497 solver.cpp:56] Solver scaffolding done.
I0314 22:54:40.302861 3497 caffe.cpp:248] Starting Optimization
I0314 22:54:40.302898 3497 solver.cpp:273] Solving
I0314 22:54:40.302913 3497 solver.cpp:274] Learning Rate Policy: step
I0314 22:54:40.422722 3497 solver.cpp:331] Iteration 0, Testing net (#0)
I0314 22:54:40.422821 3497 net.cpp:676] Ignoring source layer train-data
I0314 22:54:40.422837 3497 net.cpp:676] Ignoring source layer label_train-data_1_split
I0314 22:54:41.517745 3497 solver.cpp:398] Test net output #0: accuracy = 0.625
I0314 22:54:41.517810 3497 solver.cpp:398] Test net output #1: loss = 0.68609 (* 1 = 0.68609 loss)
I0314 22:54:41.517830 3497 solver.cpp:398] Test net output #2: loss1/accuracy = 0.375
I0314 22:54:41.517850 3497 solver.cpp:398] Test net output #3: loss1/loss = 1.95146 (* 0.3 = 0.585438 loss)
I0314 22:54:41.517868 3497 solver.cpp:398] Test net output #4: loss2/accuracy = 0.375
I0314 22:54:41.517885 3497 solver.cpp:398] Test net output #5: loss2/loss = 0.781426 (* 0.3 = 0.234428 loss)

[sulthanashafi]

I0405 07:31:38.302242 10805 net.cpp:159] Memory required for data: 2639662980
I0405 07:31:38.302245 10805 net.cpp:222] mAP does not need backward computation.
I0405 07:31:38.302249 10805 net.cpp:222] score does not need backward computation.
I0405 07:31:38.302253 10805 net.cpp:222] cluster_gt does not need backward computation.
I0405 07:31:38.302258 10805 net.cpp:222] cluster does not need backward computation.
I0405 07:31:38.302263 10805 net.cpp:220] coverage_loss needs backward computation.
I0405 07:31:38.302266 10805 net.cpp:220] bbox_loss needs backward computation.
I0405 07:31:38.302271 10805 net.cpp:220] bbox-obj-norm needs backward computation.
I0405 07:31:38.302276 10805 net.cpp:220] bbox-norm needs backward computation.
I0405 07:31:38.302280 10805 net.cpp:220] bbox_mask needs backward computation.
I0405 07:31:38.302309 10805 net.cpp:220] bboxes_bbox/regressor_0_split needs backward computation.
I0405 07:31:38.302314 10805 net.cpp:220] bbox/regressor needs backward computation.
I0405 07:31:38.302319 10805 net.cpp:220] coverage_coverage/sig_0_split needs backward computation.
I0405 07:31:38.302322 10805 net.cpp:220] coverage/sig needs backward computation.
I0405 07:31:38.302326 10805 net.cpp:220] cvg/classifier needs backward computation.
I0405 07:31:38.302330 10805 net.cpp:220] pool5/drop_s1_pool5/drop_s1_0_split needs backward computation.
I0405 07:31:38.302335 10805 net.cpp:220] pool5/drop_s1 needs backward computation.
I0405 07:31:38.302338 10805 net.cpp:220] inception_5b/output needs backward computation.
I0405 07:31:38.302345 10805 net.cpp:220] inception_5b/relu_pool_proj needs backward computation.
I0405 07:31:38.302348 10805 net.cpp:220] inception_5b/pool_proj needs backward computation.
I0405 07:31:38.302352 10805 net.cpp:220] inception_5b/pool needs backward computation.
I0405 07:31:38.302356 10805 net.cpp:220] inception_5b/relu_5x5 needs backward computation.
I0405 07:31:38.302361 10805 net.cpp:220] inception_5b/5x5 needs backward computation.
I0405 07:31:38.302366 10805 net.cpp:220] inception_5b/relu_5x5_reduce needs backward computation.
I0405 07:31:38.302369 10805 net.cpp:220] inception_5b/5x5_reduce needs backward computation.
I0405 07:31:38.302373 10805 net.cpp:220] inception_5b/relu_3x3 needs backward computation.
I0405 07:31:38.302376 10805 net.cpp:220] inception_5b/3x3 needs backward computation.
I0405 07:31:38.302381 10805 net.cpp:220] inception_5b/relu_3x3_reduce needs backward computation.
I0405 07:31:38.302384 10805 net.cpp:220] inception_5b/3x3_reduce needs backward computation.
I0405 07:31:38.302388 10805 net.cpp:220] inception_5b/relu_1x1 needs backward computation.
I0405 07:31:38.302392 10805 net.cpp:220] inception_5b/1x1 needs backward computation.
I0405 07:31:38.302397 10805 net.cpp:220] inception_5a/output_inception_5a/output_0_split needs backward computation.
I0405 07:31:38.302400 10805 net.cpp:220] inception_5a/output needs backward computation.
I0405 07:31:38.302407 10805 net.cpp:220] inception_5a/relu_pool_proj needs backward computation.
I0405 07:31:38.302410 10805 net.cpp:220] inception_5a/pool_proj needs backward computation.
I0405 07:31:38.302414 10805 net.cpp:220] inception_5a/pool needs backward computation.
I0405 07:31:38.302418 10805 net.cpp:220] inception_5a/relu_5x5 needs backward computation.
I0405 07:31:38.302423 10805 net.cpp:220] inception_5a/5x5 needs backward computation.
I0405 07:31:38.302426 10805 net.cpp:220] inception_5a/relu_5x5_reduce needs backward computation.
I0405 07:31:38.302430 10805 net.cpp:220] inception_5a/5x5_reduce needs backward computation.
I0405 07:31:38.302434 10805 net.cpp:220] inception_5a/relu_3x3 needs backward computation.
I0405 07:31:38.302438 10805 net.cpp:220] inception_5a/3x3 needs backward computation.
I0405 07:31:38.302443 10805 net.cpp:220] inception_5a/relu_3x3_reduce needs backward computation.
I0405 07:31:38.302445 10805 net.cpp:220] inception_5a/3x3_reduce needs backward computation.
I0405 07:31:38.302449 10805 net.cpp:220] inception_5a/relu_1x1 needs backward computation.
I0405 07:31:38.302453 10805 net.cpp:220] inception_5a/1x1 needs backward computation.
I0405 07:31:38.302458 10805 net.cpp:220] inception_4e/output_inception_4e/output_0_split needs backward computation.
I0405 07:31:38.302461 10805 net.cpp:220] inception_4e/output needs backward computation.
I0405 07:31:38.302467 10805 net.cpp:220] inception_4e/relu_pool_proj needs backward computation.
I0405 07:31:38.302470 10805 net.cpp:220] inception_4e/pool_proj needs backward computation.
I0405 07:31:38.302477 10805 net.cpp:220] inception_4e/pool needs backward computation.
I0405 07:31:38.302481 10805 net.cpp:220] inception_4e/relu_5x5 needs backward computation.
I0405 07:31:38.302485 10805 net.cpp:220] inception_4e/5x5 needs backward computation.
I0405 07:31:38.302489 10805 net.cpp:220] inception_4e/relu_5x5_reduce needs backward computation.
I0405 07:31:38.302500 10805 net.cpp:220] inception_4e/5x5_reduce needs backward computation.
I0405 07:31:38.302503 10805 net.cpp:220] inception_4e/relu_3x3 needs backward computation.
I0405 07:31:38.302507 10805 net.cpp:220] inception_4e/3x3 needs backward computation.
I0405 07:31:38.302511 10805 net.cpp:220] inception_4e/relu_3x3_reduce needs backward computation.
I0405 07:31:38.302515 10805 net.cpp:220] inception_4e/3x3_reduce needs backward computation.
I0405 07:31:38.302518 10805 net.cpp:220] inception_4e/relu_1x1 needs backward computation.
I0405 07:31:38.302522 10805 net.cpp:220] inception_4e/1x1 needs backward computation.
I0405 07:31:38.302526 10805 net.cpp:220] inception_4d/output_inception_4d/output_0_split needs backward computation.
I0405 07:31:38.302531 10805 net.cpp:220] inception_4d/output needs backward computation.
I0405 07:31:38.302536 10805 net.cpp:220] inception_4d/relu_pool_proj needs backward computation.
I0405 07:31:38.302539 10805 net.cpp:220] inception_4d/pool_proj needs backward computation.
I0405 07:31:38.302544 10805 net.cpp:220] inception_4d/pool needs backward computation.
I0405 07:31:38.302548 10805 net.cpp:220] inception_4d/relu_5x5 needs backward computation.
I0405 07:31:38.302551 10805 net.cpp:220] inception_4d/5x5 needs backward computation.
I0405 07:31:38.302556 10805 net.cpp:220] inception_4d/relu_5x5_reduce needs backward computation.
I0405 07:31:38.302559 10805 net.cpp:220] inception_4d/5x5_reduce needs backward computation.
I0405 07:31:38.302563 10805 net.cpp:220] inception_4d/relu_3x3 needs backward computation.
I0405 07:31:38.302567 10805 net.cpp:220] inception_4d/3x3 needs backward computation.
I0405 07:31:38.302570 10805 net.cpp:220] inception_4d/relu_3x3_reduce needs backward computation.
I0405 07:31:38.302573 10805 net.cpp:220] inception_4d/3x3_reduce needs backward computation.
I0405 07:31:38.302577 10805 net.cpp:220] inception_4d/relu_1x1 needs backward computation.
I0405 07:31:38.302580 10805 net.cpp:220] inception_4d/1x1 needs backward computation.
I0405 07:31:38.302584 10805 net.cpp:220] inception_4c/output_inception_4c/output_0_split needs backward computation.
I0405 07:31:38.302588 10805 net.cpp:220] inception_4c/output needs backward computation.
I0405 07:31:38.302593 10805 net.cpp:220] inception_4c/relu_pool_proj needs backward computation.
I0405 07:31:38.302597 10805 net.cpp:220] inception_4c/pool_proj needs backward computation.
I0405 07:31:38.302601 10805 net.cpp:220] inception_4c/pool needs backward computation.
I0405 07:31:38.302605 10805 net.cpp:220] inception_4c/relu_5x5 needs backward computation.
I0405 07:31:38.302608 10805 net.cpp:220] inception_4c/5x5 needs backward computation.
I0405 07:31:38.302613 10805 net.cpp:220] inception_4c/relu_5x5_reduce needs backward computation.
I0405 07:31:38.302616 10805 net.cpp:220] inception_4c/5x5_reduce needs backward computation.
I0405 07:31:38.302619 10805 net.cpp:220] inception_4c/relu_3x3 needs backward computation.
I0405 07:31:38.302623 10805 net.cpp:220] inception_4c/3x3 needs backward computation.
I0405 07:31:38.302628 10805 net.cpp:220] inception_4c/relu_3x3_reduce needs backward computation.
I0405 07:31:38.302630 10805 net.cpp:220] inception_4c/3x3_reduce needs backward computation.
I0405 07:31:38.302634 10805 net.cpp:220] inception_4c/relu_1x1 needs backward computation.
I0405 07:31:38.302637 10805 net.cpp:220] inception_4c/1x1 needs backward computation.
I0405 07:31:38.302641 10805 net.cpp:220] inception_4b/output_inception_4b/output_0_split needs backward computation.
I0405 07:31:38.302645 10805 net.cpp:220] inception_4b/output needs backward computation.
I0405 07:31:38.302649 10805 net.cpp:220] inception_4b/relu_pool_proj needs backward computation.
I0405 07:31:38.302654 10805 net.cpp:220] inception_4b/pool_proj needs backward computation.
I0405 07:31:38.302656 10805 net.cpp:220] inception_4b/pool needs backward computation.
I0405 07:31:38.302660 10805 net.cpp:220] inception_4b/relu_5x5 needs backward computation.
I0405 07:31:38.302664 10805 net.cpp:220] inception_4b/5x5 needs backward computation.
I0405 07:31:38.302673 10805 net.cpp:220] inception_4b/relu_5x5_reduce needs backward computation.
I0405 07:31:38.302677 10805 net.cpp:220] inception_4b/5x5_reduce needs backward computation.
I0405 07:31:38.302680 10805 net.cpp:220] inception_4b/relu_3x3 needs backward computation.
I0405 07:31:38.302685 10805 net.cpp:220] inception_4b/3x3 needs backward computation.
I0405 07:31:38.302712 10805 net.cpp:220] inception_4b/relu_3x3_reduce needs backward computation.
I0405 07:31:38.302718 10805 net.cpp:220] inception_4b/3x3_reduce needs backward computation.
I0405 07:31:38.302722 10805 net.cpp:220] inception_4b/relu_1x1 needs backward computation.
I0405 07:31:38.302726 10805 net.cpp:220] inception_4b/1x1 needs backward computation.
I0405 07:31:38.302737 10805 net.cpp:220] inception_4a/output_inception_4a/output_0_split needs backward computation.
I0405 07:31:38.302742 10805 net.cpp:220] inception_4a/output needs backward computation.
I0405 07:31:38.302747 10805 net.cpp:220] inception_4a/relu_pool_proj needs backward computation.
I0405 07:31:38.302750 10805 net.cpp:220] inception_4a/pool_proj needs backward computation.
I0405 07:31:38.302754 10805 net.cpp:220] inception_4a/pool needs backward computation.
I0405 07:31:38.302758 10805 net.cpp:220] inception_4a/relu_5x5 needs backward computation.
I0405 07:31:38.302762 10805 net.cpp:220] inception_4a/5x5 needs backward computation.
I0405 07:31:38.302767 10805 net.cpp:220] inception_4a/relu_5x5_reduce needs backward computation.
I0405 07:31:38.302770 10805 net.cpp:220] inception_4a/5x5_reduce needs backward computation.
I0405 07:31:38.302774 10805 net.cpp:220] inception_4a/relu_3x3 needs backward computation.
I0405 07:31:38.302778 10805 net.cpp:220] inception_4a/3x3 needs backward computation.
I0405 07:31:38.302781 10805 net.cpp:220] inception_4a/relu_3x3_reduce needs backward computation.
I0405 07:31:38.302785 10805 net.cpp:220] inception_4a/3x3_reduce needs backward computation.
I0405 07:31:38.302789 10805 net.cpp:220] inception_4a/relu_1x1 needs backward computation.
I0405 07:31:38.302793 10805 net.cpp:220] inception_4a/1x1 needs backward computation.
I0405 07:31:38.302798 10805 net.cpp:220] pool3/3x3_s2_pool3/3x3_s2_0_split needs backward computation.
I0405 07:31:38.302801 10805 net.cpp:220] pool3/3x3_s2 needs backward computation.
I0405 07:31:38.302805 10805 net.cpp:220] inception_3b/output needs backward computation.
I0405 07:31:38.302811 10805 net.cpp:220] inception_3b/relu_pool_proj needs backward computation.
I0405 07:31:38.302815 10805 net.cpp:220] inception_3b/pool_proj needs backward computation.
I0405 07:31:38.302819 10805 net.cpp:220] inception_3b/pool needs backward computation.
I0405 07:31:38.302822 10805 net.cpp:220] inception_3b/relu_5x5 needs backward computation.
I0405 07:31:38.302826 10805 net.cpp:220] inception_3b/5x5 needs backward computation.
I0405 07:31:38.302830 10805 net.cpp:220] inception_3b/relu_5x5_reduce needs backward computation.
I0405 07:31:38.302835 10805 net.cpp:220] inception_3b/5x5_reduce needs backward computation.
I0405 07:31:38.302839 10805 net.cpp:220] inception_3b/relu_3x3 needs backward computation.
I0405 07:31:38.302844 10805 net.cpp:220] inception_3b/3x3 needs backward computation.
I0405 07:31:38.302847 10805 net.cpp:220] inception_3b/relu_3x3_reduce needs backward computation.
I0405 07:31:38.302850 10805 net.cpp:220] inception_3b/3x3_reduce needs backward computation.
I0405 07:31:38.302855 10805 net.cpp:220] inception_3b/relu_1x1 needs backward computation.
I0405 07:31:38.302858 10805 net.cpp:220] inception_3b/1x1 needs backward computation.
I0405 07:31:38.302862 10805 net.cpp:220] inception_3a/output_inception_3a/output_0_split needs backward computation.
I0405 07:31:38.302866 10805 net.cpp:220] inception_3a/output needs backward computation.
I0405 07:31:38.302872 10805 net.cpp:220] inception_3a/relu_pool_proj needs backward computation.
I0405 07:31:38.302876 10805 net.cpp:220] inception_3a/pool_proj needs backward computation.
I0405 07:31:38.302881 10805 net.cpp:220] inception_3a/pool needs backward computation.
I0405 07:31:38.302886 10805 net.cpp:220] inception_3a/relu_5x5 needs backward computation.
I0405 07:31:38.302896 10805 net.cpp:220] inception_3a/5x5 needs backward computation.
I0405 07:31:38.302901 10805 net.cpp:220] inception_3a/relu_5x5_reduce needs backward computation.
I0405 07:31:38.302904 10805 net.cpp:220] inception_3a/5x5_reduce needs backward computation.
I0405 07:31:38.302908 10805 net.cpp:220] inception_3a/relu_3x3 needs backward computation.
I0405 07:31:38.302912 10805 net.cpp:220] inception_3a/3x3 needs backward computation.
I0405 07:31:38.302916 10805 net.cpp:220] inception_3a/relu_3x3_reduce needs backward computation.
I0405 07:31:38.302919 10805 net.cpp:220] inception_3a/3x3_reduce needs backward computation.
I0405 07:31:38.302923 10805 net.cpp:220] inception_3a/relu_1x1 needs backward computation.
I0405 07:31:38.302927 10805 net.cpp:220] inception_3a/1x1 needs backward computation.
I0405 07:31:38.302932 10805 net.cpp:220] pool2/3x3_s2_pool2/3x3_s2_0_split needs backward computation.
I0405 07:31:38.302939 10805 net.cpp:220] pool2/3x3_s2 needs backward computation.
I0405 07:31:38.302943 10805 net.cpp:220] conv2/norm2 needs backward computation.
I0405 07:31:38.302947 10805 net.cpp:220] conv2/relu_3x3 needs backward computation.
I0405 07:31:38.302952 10805 net.cpp:220] conv2/3x3 needs backward computation.
I0405 07:31:38.302956 10805 net.cpp:220] conv2/relu_3x3_reduce needs backward computation.
I0405 07:31:38.302960 10805 net.cpp:220] conv2/3x3_reduce needs backward computation.
I0405 07:31:38.302964 10805 net.cpp:220] pool1/norm1 needs backward computation.
I0405 07:31:38.302968 10805 net.cpp:220] pool1/3x3_s2 needs backward computation.
I0405 07:31:38.302973 10805 net.cpp:220] conv1/relu_7x7 needs backward computation.
I0405 07:31:38.302976 10805 net.cpp:220] conv1/7x7_s2 needs backward computation.
I0405 07:31:38.302980 10805 net.cpp:222] bb-obj-norm does not need backward computation.
I0405 07:31:38.302986 10805 net.cpp:222] bb-label-norm does not need backward computation.
I0405 07:31:38.302994 10805 net.cpp:222] obj-block_obj-block_0_split does not need backward computation.
I0405 07:31:38.302997 10805 net.cpp:222] obj-block does not need backward computation.
I0405 07:31:38.303004 10805 net.cpp:222] size-block_size-block_0_split does not need backward computation.
I0405 07:31:38.303009 10805 net.cpp:222] size-block does not need backward computation.
I0405 07:31:38.303015 10805 net.cpp:222] coverage-block does not need backward computation.
I0405 07:31:38.303022 10805 net.cpp:222] coverage-label_slice-label_4_split does not need backward computation.
I0405 07:31:38.303028 10805 net.cpp:222] obj-label_slice-label_3_split does not need backward computation.
I0405 07:31:38.303033 10805 net.cpp:222] size-label_slice-label_2_split does not need backward computation.
I0405 07:31:38.303038 10805 net.cpp:222] bbox-label_slice-label_1_split does not need backward computation.
I0405 07:31:38.303045 10805 net.cpp:222] foreground-label_slice-label_0_split does not need backward computation.
I0405 07:31:38.303050 10805 net.cpp:222] slice-label does not need backward computation.
I0405 07:31:38.303056 10805 net.cpp:222] val_transform does not need backward computation.
I0405 07:31:38.303061 10805 net.cpp:222] val_label does not need backward computation.
I0405 07:31:38.303064 10805 net.cpp:222] val_data does not need backward computation.
I0405 07:31:38.303067 10805 net.cpp:264] This network produces output loss_bbox
I0405 07:31:38.303072 10805 net.cpp:264] This network produces output loss_coverage
I0405 07:31:38.303076 10805 net.cpp:264] This network produces output mAP
I0405 07:31:38.303081 10805 net.cpp:264] This network produces output precision
I0405 07:31:38.303083 10805 net.cpp:264] This network produces output recall
I0405 07:31:38.303221 10805 net.cpp:284] Network initialization done.
I0405 07:31:38.304024 10805 solver.cpp:60] Solver scaffolding done.
I0405 07:31:38.308969 10805 caffe.cpp:135] Finetuning from /home/ubuntu/DIGITS/examples/object-detection/bvlc_googlenet.caffemodel
I0405 07:31:38.391417 10805 upgrade_proto.cpp:52] Attempting to upgrade input file specified using deprecated V1LayerParameter: /home/ubuntu/DIGITS/examples/object-detection/bvlc_googlenet.caffemodel
I0405 07:31:38.449021 10805 upgrade_proto.cpp:60] Successfully upgraded file specified using deprecated V1LayerParameter
I0405 07:31:38.449602 10805 net.cpp:791] Ignoring source layer data
I0405 07:31:38.449610 10805 net.cpp:791] Ignoring source layer label_data_1_split
I0405 07:31:38.450469 10805 net.cpp:791] Ignoring source layer loss1/ave_pool
I0405 07:31:38.450475 10805 net.cpp:791] Ignoring source layer loss1/conv
I0405 07:31:38.450479 10805 net.cpp:791] Ignoring source layer loss1/relu_conv
I0405 07:31:38.450482 10805 net.cpp:791] Ignoring source layer loss1/fc
I0405 07:31:38.450485 10805 net.cpp:791] Ignoring source layer loss1/relu_fc
I0405 07:31:38.450489 10805 net.cpp:791] Ignoring source layer loss1/drop_fc
I0405 07:31:38.450494 10805 net.cpp:791] Ignoring source layer loss1/classifier
I0405 07:31:38.450496 10805 net.cpp:791] Ignoring source layer loss1/loss
I0405 07:31:38.451746 10805 net.cpp:791] Ignoring source layer loss2/ave_pool
I0405 07:31:38.451752 10805 net.cpp:791] Ignoring source layer loss2/conv
I0405 07:31:38.451756 10805 net.cpp:791] Ignoring source layer loss2/relu_conv
I0405 07:31:38.451759 10805 net.cpp:791] Ignoring source layer loss2/fc
I0405 07:31:38.451762 10805 net.cpp:791] Ignoring source layer loss2/relu_fc
I0405 07:31:38.451766 10805 net.cpp:791] Ignoring source layer loss2/drop_fc
I0405 07:31:38.451769 10805 net.cpp:791] Ignoring source layer loss2/classifier
I0405 07:31:38.451772 10805 net.cpp:791] Ignoring source layer loss2/loss
I0405 07:31:38.452405 10805 net.cpp:791] Ignoring source layer pool4/3x3_s2
I0405 07:31:38.452411 10805 net.cpp:791] Ignoring source layer pool4/3x3_s2_pool4/3x3_s2_0_split
I0405 07:31:38.454190 10805 net.cpp:791] Ignoring source layer pool5/7x7_s1
I0405 07:31:38.454195 10805 net.cpp:791] Ignoring source layer pool5/drop_7x7_s1
I0405 07:31:38.454198 10805 net.cpp:791] Ignoring source layer loss3/classifier
I0405 07:31:38.454202 10805 net.cpp:791] Ignoring source layer loss3/loss3
I0405 07:31:38.543020 10805 upgrade_proto.cpp:52] Attempting to upgrade input file specified using deprecated V1LayerParameter: /home/ubuntu/DIGITS/examples/object-detection/bvlc_googlenet.caffemodel
I0405 07:31:38.599452 10805 upgrade_proto.cpp:60] Successfully upgraded file specified using deprecated V1LayerParameter
I0405 07:31:38.599731 10805 net.cpp:791] Ignoring source layer data
I0405 07:31:38.599737 10805 net.cpp:791] Ignoring source layer label_data_1_split
I0405 07:31:38.600605 10805 net.cpp:791] Ignoring source layer loss1/ave_pool
I0405 07:31:38.600611 10805 net.cpp:791] Ignoring source layer loss1/conv
I0405 07:31:38.600615 10805 net.cpp:791] Ignoring source layer loss1/relu_conv
I0405 07:31:38.600618 10805 net.cpp:791] Ignoring source layer loss1/fc
I0405 07:31:38.600622 10805 net.cpp:791] Ignoring source layer loss1/relu_fc
I0405 07:31:38.600626 10805 net.cpp:791] Ignoring source layer loss1/drop_fc
I0405 07:31:38.600630 10805 net.cpp:791] Ignoring source layer loss1/classifier
I0405 07:31:38.600633 10805 net.cpp:791] Ignoring source layer loss1/loss
I0405 07:31:38.601871 10805 net.cpp:791] Ignoring source layer loss2/ave_pool
I0405 07:31:38.601876 10805 net.cpp:791] Ignoring source layer loss2/conv
I0405 07:31:38.601879 10805 net.cpp:791] Ignoring source layer loss2/relu_conv
I0405 07:31:38.601883 10805 net.cpp:791] Ignoring source layer loss2/fc
I0405 07:31:38.601886 10805 net.cpp:791] Ignoring source layer loss2/relu_fc
I0405 07:31:38.601889 10805 net.cpp:791] Ignoring source layer loss2/drop_fc
I0405 07:31:38.601892 10805 net.cpp:791] Ignoring source layer loss2/classifier
I0405 07:31:38.601897 10805 net.cpp:791] Ignoring source layer loss2/loss
I0405 07:31:38.602520 10805 net.cpp:791] Ignoring source layer pool4/3x3_s2
I0405 07:31:38.602526 10805 net.cpp:791] Ignoring source layer pool4/3x3_s2_pool4/3x3_s2_0_split
I0405 07:31:38.604306 10805 net.cpp:791] Ignoring source layer pool5/7x7_s1
I0405 07:31:38.604313 10805 net.cpp:791] Ignoring source layer pool5/drop_7x7_s1
I0405 07:31:38.604343 10805 net.cpp:791] Ignoring source layer loss3/classifier
I0405 07:31:38.604346 10805 net.cpp:791] Ignoring source layer loss3/loss3
I0405 07:31:38.610388 10805 caffe.cpp:231] Starting Optimization
I0405 07:31:38.610404 10805 solver.cpp:304] Solving
I0405 07:31:38.610407 10805 solver.cpp:305] Learning Rate Policy: step
I0405 07:31:38.616950 10805 solver.cpp:362] Iteration 0, Testing net (#0)
I0405 07:31:38.616967 10805 net.cpp:723] Ignoring source layer train_data
I0405 07:31:38.616971 10805 net.cpp:723] Ignoring source layer train_label
I0405 07:31:38.616974 10805 net.cpp:723] Ignoring source layer train_transform
I0405 07:32:24.327752 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 07:32:24.327882 10805 solver.cpp:429] Test net output #1: loss_coverage = 37.2286 (* 1 = 37.2286 loss)
I0405 07:32:24.327898 10805 solver.cpp:429] Test net output #2: mAP = 0
I0405 07:32:24.327903 10805 solver.cpp:429] Test net output #3: precision = 0
I0405 07:32:24.327908 10805 solver.cpp:429] Test net output #4: recall = 0
I0405 07:32:53.049880 10805 solver.cpp:242] Iteration 0 (0 iter/s, 74.4405s/125 iter), loss = 185.764
I0405 07:32:53.049921 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 07:32:53.049929 10805 solver.cpp:261] Train net output #1: loss_coverage = 196.138 (* 1 = 196.138 loss)
I0405 07:32:53.049954 10805 sgd_solver.cpp:106] Iteration 0, lr = 0.0001
I0405 07:40:03.954133 10805 solver.cpp:242] Iteration 125 (0.290083 iter/s, 430.911s/125 iter), loss = 0.000555313
I0405 07:40:03.954197 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 07:40:03.954206 10805 solver.cpp:261] Train net output #1: loss_coverage = 0.000211057 (* 1 = 0.000211057 loss)
I0405 07:40:03.954217 10805 sgd_solver.cpp:106] Iteration 125, lr = 0.0001
I0405 07:47:13.932087 10805 solver.cpp:242] Iteration 250 (0.290708 iter/s, 429.984s/125 iter), loss = 0.000184559
I0405 07:47:13.932155 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 07:47:13.932164 10805 solver.cpp:261] Train net output #1: loss_coverage = 0.000198643 (* 1 = 0.000198643 loss)
I0405 07:47:13.932175 10805 sgd_solver.cpp:106] Iteration 250, lr = 0.0001
I0405 07:54:24.201158 10805 solver.cpp:242] Iteration 375 (0.290512 iter/s, 430.276s/125 iter), loss = 1.11369e-05
I0405 07:54:24.201268 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 07:54:24.201279 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.27858e-07 (* 1 = 4.27858e-07 loss)
I0405 07:54:24.201292 10805 sgd_solver.cpp:106] Iteration 375, lr = 0.0001
I0405 08:01:34.949679 10805 solver.cpp:242] Iteration 500 (0.290188 iter/s, 430.755s/125 iter), loss = 6.95455e-06
I0405 08:01:34.949753 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 08:01:34.949762 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.40064e-07 (* 1 = 1.40064e-07 loss)
I0405 08:01:34.949774 10805 sgd_solver.cpp:106] Iteration 500, lr = 0.0001
I0405 08:08:45.109619 10805 solver.cpp:242] Iteration 625 (0.290585 iter/s, 430.166s/125 iter), loss = 7.43293e-06
I0405 08:08:45.109740 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 08:08:45.109750 10805 solver.cpp:261] Train net output #1: loss_coverage = 5.08794e-07 (* 1 = 5.08794e-07 loss)
I0405 08:08:45.109762 10805 sgd_solver.cpp:106] Iteration 625, lr = 0.0001
I0405 08:15:56.125247 10805 solver.cpp:242] Iteration 750 (0.290008 iter/s, 431.022s/125 iter), loss = 6.5936e-06
I0405 08:15:56.125321 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 08:15:56.125330 10805 solver.cpp:261] Train net output #1: loss_coverage = 9.4829e-08 (* 1 = 9.4829e-08 loss)
I0405 08:15:56.125341 10805 sgd_solver.cpp:106] Iteration 750, lr = 0.0001
I0405 08:23:06.809845 10805 solver.cpp:242] Iteration 875 (0.290231 iter/s, 430.691s/125 iter), loss = 6.58587e-06
I0405 08:23:06.809952 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 08:23:06.809962 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.47024e-08 (* 1 = 2.47024e-08 loss)
I0405 08:23:06.809973 10805 sgd_solver.cpp:106] Iteration 875, lr = 0.0001
I0405 08:30:13.902102 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_1000.caffemodel
I0405 08:30:14.075453 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_1000.solverstate
I0405 08:30:14.154969 10805 solver.cpp:362] Iteration 1000, Testing net (#0)
I0405 08:30:14.154994 10805 net.cpp:723] Ignoring source layer train_data
I0405 08:30:14.154999 10805 net.cpp:723] Ignoring source layer train_label
I0405 08:30:14.155001 10805 net.cpp:723] Ignoring source layer train_transform
I0405 08:30:46.368716 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 08:30:46.368768 10805 solver.cpp:429] Test net output #1: loss_coverage = 2.5254e-09 (* 1 = 2.5254e-09 loss)
I0405 08:30:46.368774 10805 solver.cpp:429] Test net output #2: mAP = 0
I0405 08:30:46.368779 10805 solver.cpp:429] Test net output #3: precision = 0
I0405 08:30:46.368783 10805 solver.cpp:429] Test net output #4: recall = 0
I0405 08:30:49.844825 10805 solver.cpp:242] Iteration 1000 (0.269954 iter/s, 463.042s/125 iter), loss = 6.62253e-06
I0405 08:30:49.844871 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 08:30:49.844879 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.88123e-09 (* 1 = 4.88123e-09 loss)
I0405 08:30:49.844892 10805 sgd_solver.cpp:106] Iteration 1000, lr = 0.0001
I0405 08:38:01.590390 10805 solver.cpp:242] Iteration 1125 (0.289518 iter/s, 431.752s/125 iter), loss = 6.53392e-06
I0405 08:38:01.590512 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 08:38:01.590523 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.53214e-08 (* 1 = 1.53214e-08 loss)
I0405 08:38:01.590536 10805 sgd_solver.cpp:106] Iteration 1125, lr = 0.0001
I0405 08:45:12.595553 10805 solver.cpp:242] Iteration 1250 (0.290015 iter/s, 431.012s/125 iter), loss = 6.57547e-06
I0405 08:45:12.595669 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 08:45:12.595679 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.36113e-08 (* 1 = 3.36113e-08 loss)
I0405 08:45:12.595690 10805 sgd_solver.cpp:106] Iteration 1250, lr = 0.0001
I0405 08:52:23.706305 10805 solver.cpp:242] Iteration 1375 (0.289944 iter/s, 431.117s/125 iter), loss = 6.5818e-06
I0405 08:52:23.706420 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 08:52:23.706430 10805 solver.cpp:261] Train net output #1: loss_coverage = 6.63541e-08 (* 1 = 6.63541e-08 loss)
I0405 08:52:23.706444 10805 sgd_solver.cpp:106] Iteration 1375, lr = 0.0001
I0405 08:59:38.584282 10805 solver.cpp:242] Iteration 1500 (0.287433 iter/s, 434.884s/125 iter), loss = 6.54109e-06
I0405 08:59:38.584388 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 08:59:38.584398 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.83484e-09 (* 1 = 1.83484e-09 loss)
I0405 08:59:38.584409 10805 sgd_solver.cpp:106] Iteration 1500, lr = 0.0001
I0405 09:06:49.712990 10805 solver.cpp:242] Iteration 1625 (0.289932 iter/s, 431.135s/125 iter), loss = 6.54078e-06
I0405 09:06:49.713052 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 09:06:49.713062 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.30632e-08 (* 1 = 2.30632e-08 loss)
I0405 09:06:49.713073 10805 sgd_solver.cpp:106] Iteration 1625, lr = 0.0001
I0405 09:14:00.508719 10805 solver.cpp:242] Iteration 1750 (0.290156 iter/s, 430.802s/125 iter), loss = 6.54784e-06
I0405 09:14:00.508831 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 09:14:00.508841 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.27617e-09 (* 1 = 1.27617e-09 loss)
I0405 09:14:00.508854 10805 sgd_solver.cpp:106] Iteration 1750, lr = 0.0001
I0405 09:21:11.027292 10805 solver.cpp:242] Iteration 1875 (0.290343 iter/s, 430.525s/125 iter), loss = 6.53608e-06
I0405 09:21:11.027410 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 09:21:11.027421 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.06149e-08 (* 1 = 1.06149e-08 loss)
I0405 09:21:11.027432 10805 sgd_solver.cpp:106] Iteration 1875, lr = 0.0001
I0405 09:28:18.673650 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_2000.caffemodel
I0405 09:28:18.770432 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_2000.solverstate
I0405 09:28:18.845625 10805 solver.cpp:362] Iteration 2000, Testing net (#0)
I0405 09:28:18.845649 10805 net.cpp:723] Ignoring source layer train_data
I0405 09:28:18.845652 10805 net.cpp:723] Ignoring source layer train_label
I0405 09:28:18.845656 10805 net.cpp:723] Ignoring source layer train_transform
I0405 09:28:51.019788 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 09:28:51.019839 10805 solver.cpp:429] Test net output #1: loss_coverage = 4.84738e-10 (* 1 = 4.84738e-10 loss)
I0405 09:28:51.019845 10805 solver.cpp:429] Test net output #2: mAP = 0
I0405 09:28:51.019850 10805 solver.cpp:429] Test net output #3: precision = 0
I0405 09:28:51.019853 10805 solver.cpp:429] Test net output #4: recall = 0
I0405 09:28:54.442570 10805 solver.cpp:242] Iteration 2000 (0.269732 iter/s, 463.422s/125 iter), loss = 6.52936e-06
I0405 09:28:54.442618 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 09:28:54.442627 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.26203e-09 (* 1 = 3.26203e-09 loss)
I0405 09:28:54.442639 10805 sgd_solver.cpp:106] Iteration 2000, lr = 0.0001
I0405 09:36:04.768800 10805 solver.cpp:242] Iteration 2125 (0.290473 iter/s, 430.333s/125 iter), loss = 6.53187e-06
I0405 09:36:04.768874 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 09:36:04.768883 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.91586e-09 (* 1 = 3.91586e-09 loss)
I0405 09:36:04.768895 10805 sgd_solver.cpp:106] Iteration 2125, lr = 0.0001
I0405 09:43:16.111186 10805 solver.cpp:242] Iteration 2250 (0.289789 iter/s, 431.349s/125 iter), loss = 6.53357e-06
I0405 09:43:16.111294 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 09:43:16.111305 10805 solver.cpp:261] Train net output #1: loss_coverage = 9.55734e-09 (* 1 = 9.55734e-09 loss)
I0405 09:43:16.111318 10805 sgd_solver.cpp:106] Iteration 2250, lr = 0.0001
I0405 09:50:27.727860 10805 solver.cpp:242] Iteration 2375 (0.289604 iter/s, 431.623s/125 iter), loss = 6.5452e-06
I0405 09:50:27.727929 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 09:50:27.727938 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.07198e-08 (* 1 = 3.07198e-08 loss)
I0405 09:50:27.727951 10805 sgd_solver.cpp:106] Iteration 2375, lr = 0.0001
I0405 09:57:38.621101 10805 solver.cpp:242] Iteration 2500 (0.290091 iter/s, 430.9s/125 iter), loss = 6.5351e-06
I0405 09:57:38.621173 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 09:57:38.621183 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.59404e-09 (* 1 = 1.59404e-09 loss)
I0405 09:57:38.621196 10805 sgd_solver.cpp:106] Iteration 2500, lr = 0.0001
I0405 10:04:48.995395 10805 solver.cpp:242] Iteration 2625 (0.29044 iter/s, 430.381s/125 iter), loss = 6.61031e-06
I0405 10:04:48.995465 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 10:04:48.995476 10805 solver.cpp:261] Train net output #1: loss_coverage = 8.52904e-08 (* 1 = 8.52904e-08 loss)
I0405 10:04:48.995487 10805 sgd_solver.cpp:106] Iteration 2625, lr = 0.0001
I0405 10:11:59.327877 10805 solver.cpp:242] Iteration 2750 (0.290469 iter/s, 430.339s/125 iter), loss = 6.53092e-06
I0405 10:11:59.328006 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 10:11:59.328016 10805 solver.cpp:261] Train net output #1: loss_coverage = 5.19372e-10 (* 1 = 5.19372e-10 loss)
I0405 10:11:59.328029 10805 sgd_solver.cpp:106] Iteration 2750, lr = 0.0001
I0405 10:19:10.767535 10805 solver.cpp:242] Iteration 2875 (0.289723 iter/s, 431.446s/125 iter), loss = 6.52986e-06
I0405 10:19:10.767607 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 10:19:10.767616 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.13752e-09 (* 1 = 2.13752e-09 loss)
I0405 10:19:10.767628 10805 sgd_solver.cpp:106] Iteration 2875, lr = 0.0001
I0405 10:26:18.753135 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_3000.caffemodel
I0405 10:26:18.849423 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_3000.solverstate
I0405 10:26:18.924594 10805 solver.cpp:362] Iteration 3000, Testing net (#0)
I0405 10:26:18.924618 10805 net.cpp:723] Ignoring source layer train_data
I0405 10:26:18.924623 10805 net.cpp:723] Ignoring source layer train_label
I0405 10:26:18.924625 10805 net.cpp:723] Ignoring source layer train_transform
I0405 10:26:51.054725 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 10:26:51.054814 10805 solver.cpp:429] Test net output #1: loss_coverage = 8.3085e-10 (* 1 = 8.3085e-10 loss)
I0405 10:26:51.054821 10805 solver.cpp:429] Test net output #2: mAP = 0
I0405 10:26:51.054826 10805 solver.cpp:429] Test net output #3: precision = 0
I0405 10:26:51.054831 10805 solver.cpp:429] Test net output #4: recall = 0
I0405 10:26:54.495252 10805 solver.cpp:242] Iteration 3000 (0.269551 iter/s, 463.735s/125 iter), loss = 6.53555e-06
I0405 10:26:54.495306 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 10:26:54.495316 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.43668e-08 (* 1 = 1.43668e-08 loss)
I0405 10:26:54.495328 10805 sgd_solver.cpp:106] Iteration 3000, lr = 0.0001
I0405 10:34:05.892824 10805 solver.cpp:242] Iteration 3125 (0.289751 iter/s, 431.404s/125 iter), loss = 6.53267e-06
I0405 10:34:05.892890 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 10:34:05.892900 10805 solver.cpp:261] Train net output #1: loss_coverage = 5.32612e-09 (* 1 = 5.32612e-09 loss)
I0405 10:34:05.892912 10805 sgd_solver.cpp:106] Iteration 3125, lr = 0.0001
I0405 10:41:16.927286 10805 solver.cpp:242] Iteration 3250 (0.289995 iter/s, 431.041s/125 iter), loss = 6.53195e-06
I0405 10:41:16.927358 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 10:41:16.927368 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.41027e-10 (* 1 = 2.41027e-10 loss)
I0405 10:41:16.927381 10805 sgd_solver.cpp:106] Iteration 3250, lr = 0.0001
I0405 10:48:27.582367 10805 solver.cpp:242] Iteration 3375 (0.290251 iter/s, 430.662s/125 iter), loss = 6.54171e-06
I0405 10:48:27.582479 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 10:48:27.582489 10805 solver.cpp:261] Train net output #1: loss_coverage = 6.9496e-08 (* 1 = 6.9496e-08 loss)
I0405 10:48:27.582501 10805 sgd_solver.cpp:106] Iteration 3375, lr = 0.0001
I0405 10:55:37.950569 10805 solver.cpp:242] Iteration 3500 (0.290444 iter/s, 430.375s/125 iter), loss = 6.54797e-06
I0405 10:55:37.950680 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 10:55:37.950690 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.29924e-09 (* 1 = 3.29924e-09 loss)
I0405 10:55:37.950701 10805 sgd_solver.cpp:106] Iteration 3500, lr = 0.0001
I0405 11:02:49.500916 10805 solver.cpp:242] Iteration 3625 (0.289649 iter/s, 431.557s/125 iter), loss = 6.5465e-06
I0405 11:02:49.501060 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 11:02:49.501070 10805 solver.cpp:261] Train net output #1: loss_coverage = 7.7442e-09 (* 1 = 7.7442e-09 loss)
I0405 11:02:49.501082 10805 sgd_solver.cpp:106] Iteration 3625, lr = 0.0001
I0405 11:09:59.940454 10805 solver.cpp:242] Iteration 3750 (0.290396 iter/s, 430.446s/125 iter), loss = 6.54071e-06
I0405 11:09:59.940570 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 11:09:59.940582 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.39099e-08 (* 1 = 1.39099e-08 loss)
I0405 11:09:59.940593 10805 sgd_solver.cpp:106] Iteration 3750, lr = 0.0001
I0405 11:17:10.870913 10805 solver.cpp:242] Iteration 3875 (0.290066 iter/s, 430.937s/125 iter), loss = 6.57502e-06
I0405 11:17:10.870985 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 11:17:10.870993 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.91127e-10 (* 1 = 1.91127e-10 loss)
I0405 11:17:10.871006 10805 sgd_solver.cpp:106] Iteration 3875, lr = 0.0001
I0405 11:24:17.192687 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_4000.caffemodel
I0405 11:24:17.288594 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_4000.solverstate
I0405 11:24:17.363762 10805 solver.cpp:362] Iteration 4000, Testing net (#0)
I0405 11:24:17.363786 10805 net.cpp:723] Ignoring source layer train_data
I0405 11:24:17.363790 10805 net.cpp:723] Ignoring source layer train_label
I0405 11:24:17.363795 10805 net.cpp:723] Ignoring source layer train_transform
I0405 11:24:49.471812 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 11:24:49.471863 10805 solver.cpp:429] Test net output #1: loss_coverage = 8.36573e-10 (* 1 = 8.36573e-10 loss)
I0405 11:24:49.471869 10805 solver.cpp:429] Test net output #2: mAP = 0
I0405 11:24:49.471873 10805 solver.cpp:429] Test net output #3: precision = 0
I0405 11:24:49.471877 10805 solver.cpp:429] Test net output #4: recall = 0
I0405 11:24:52.864939 10805 solver.cpp:242] Iteration 4000 (0.270562 iter/s, 462.001s/125 iter), loss = 6.54231e-06
I0405 11:24:52.864984 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 11:24:52.864994 10805 solver.cpp:261] Train net output #1: loss_coverage = 9.87864e-09 (* 1 = 9.87864e-09 loss)
I0405 11:24:52.865005 10805 sgd_solver.cpp:106] Iteration 4000, lr = 0.0001
I0405 11:32:03.987061 10805 solver.cpp:242] Iteration 4125 (0.289937 iter/s, 431.129s/125 iter), loss = 6.53122e-06
I0405 11:32:03.987184 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 11:32:03.987193 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.86242e-09 (* 1 = 1.86242e-09 loss)
I0405 11:32:03.987207 10805 sgd_solver.cpp:106] Iteration 4125, lr = 0.0001
I0405 11:39:15.008373 10805 solver.cpp:242] Iteration 4250 (0.290004 iter/s, 431.028s/125 iter), loss = 6.53259e-06
I0405 11:39:15.008481 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 11:39:15.008492 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.45587e-09 (* 1 = 3.45587e-09 loss)
I0405 11:39:15.008503 10805 sgd_solver.cpp:106] Iteration 4250, lr = 0.0001
I0405 11:46:26.112397 10805 solver.cpp:242] Iteration 4375 (0.289949 iter/s, 431.111s/125 iter), loss = 6.56894e-06
I0405 11:46:26.112471 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 11:46:26.112481 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.62321e-07 (* 1 = 1.62321e-07 loss)
I0405 11:46:26.112494 10805 sgd_solver.cpp:106] Iteration 4375, lr = 0.0001
I0405 11:53:36.412757 10805 solver.cpp:242] Iteration 4500 (0.29049 iter/s, 430.307s/125 iter), loss = 6.53572e-06
I0405 11:53:36.412880 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 11:53:36.412891 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.66248e-09 (* 1 = 1.66248e-09 loss)
I0405 11:53:36.412904 10805 sgd_solver.cpp:106] Iteration 4500, lr = 0.0001
I0405 12:00:46.703377 10805 solver.cpp:242] Iteration 4625 (0.290497 iter/s, 430.297s/125 iter), loss = 6.53119e-06
I0405 12:00:46.703514 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 12:00:46.703526 10805 solver.cpp:261] Train net output #1: loss_coverage = 5.9152e-10 (* 1 = 5.9152e-10 loss)
I0405 12:00:46.703537 10805 sgd_solver.cpp:106] Iteration 4625, lr = 0.0001
I0405 12:07:57.257758 10805 solver.cpp:242] Iteration 4750 (0.290319 iter/s, 430.561s/125 iter), loss = 6.56478e-06
I0405 12:07:57.257838 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 12:07:57.257849 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.66453e-09 (* 1 = 4.66453e-09 loss)
I0405 12:07:57.257861 10805 sgd_solver.cpp:106] Iteration 4750, lr = 0.0001
I0405 12:15:11.624119 10805 solver.cpp:242] Iteration 4875 (0.287771 iter/s, 434.373s/125 iter), loss = 6.53931e-06
I0405 12:15:11.624186 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 12:15:11.624195 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.35669e-08 (* 1 = 1.35669e-08 loss)
I0405 12:15:11.624207 10805 sgd_solver.cpp:106] Iteration 4875, lr = 0.0001
I0405 12:22:18.542492 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_5000.caffemodel
I0405 12:22:18.638231 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_5000.solverstate
I0405 12:22:18.713162 10805 solver.cpp:362] Iteration 5000, Testing net (#0)
I0405 12:22:18.713186 10805 net.cpp:723] Ignoring source layer train_data
I0405 12:22:18.713191 10805 net.cpp:723] Ignoring source layer train_label
I0405 12:22:18.713194 10805 net.cpp:723] Ignoring source layer train_transform
I0405 12:22:50.890718 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 12:22:50.890771 10805 solver.cpp:429] Test net output #1: loss_coverage = 1.04422e-09 (* 1 = 1.04422e-09 loss)
I0405 12:22:50.890779 10805 solver.cpp:429] Test net output #2: mAP = 0
I0405 12:22:50.890782 10805 solver.cpp:429] Test net output #3: precision = 0
I0405 12:22:50.890787 10805 solver.cpp:429] Test net output #4: recall = 0
I0405 12:22:54.342726 10805 solver.cpp:242] Iteration 5000 (0.270138 iter/s, 462.726s/125 iter), loss = 6.534e-06
I0405 12:22:54.342775 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 12:22:54.342785 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.21598e-08 (* 1 = 1.21598e-08 loss)
I0405 12:22:54.342797 10805 sgd_solver.cpp:106] Iteration 5000, lr = 0.0001
I0405 12:30:05.207531 10805 solver.cpp:242] Iteration 5125 (0.29011 iter/s, 430.872s/125 iter), loss = 6.53531e-06
I0405 12:30:05.207597 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 12:30:05.207607 10805 solver.cpp:261] Train net output #1: loss_coverage = 9.52313e-11 (* 1 = 9.52313e-11 loss)
I0405 12:30:05.207618 10805 sgd_solver.cpp:106] Iteration 5125, lr = 0.0001
I0405 12:37:15.315502 10805 solver.cpp:242] Iteration 5250 (0.29062 iter/s, 430.115s/125 iter), loss = 6.54057e-06
I0405 12:37:15.315568 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 12:37:15.315577 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.6168e-08 (* 1 = 4.6168e-08 loss)
I0405 12:37:15.315588 10805 sgd_solver.cpp:106] Iteration 5250, lr = 0.0001
I0405 12:44:25.672062 10805 solver.cpp:242] Iteration 5375 (0.290452 iter/s, 430.363s/125 iter), loss = 6.53886e-06
I0405 12:44:25.672132 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 12:44:25.672142 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.51007e-08 (* 1 = 2.51007e-08 loss)
I0405 12:44:25.672153 10805 sgd_solver.cpp:106] Iteration 5375, lr = 0.0001
I0405 12:51:36.101763 10805 solver.cpp:242] Iteration 5500 (0.290403 iter/s, 430.436s/125 iter), loss = 6.54246e-06
I0405 12:51:36.101872 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 12:51:36.101883 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.18569e-09 (* 1 = 1.18569e-09 loss)
I0405 12:51:36.101896 10805 sgd_solver.cpp:106] Iteration 5500, lr = 0.0001
I0405 12:58:46.937023 10805 solver.cpp:242] Iteration 5625 (0.29013 iter/s, 430.842s/125 iter), loss = 6.53608e-06
I0405 12:58:46.937134 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 12:58:46.937145 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.20683e-09 (* 1 = 3.20683e-09 loss)
I0405 12:58:46.937156 10805 sgd_solver.cpp:106] Iteration 5625, lr = 0.0001
I0405 13:05:57.349730 10805 solver.cpp:242] Iteration 5750 (0.290415 iter/s, 430.419s/125 iter), loss = 6.53122e-06
I0405 13:05:57.349798 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 13:05:57.349808 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.628e-10 (* 1 = 3.628e-10 loss)
I0405 13:05:57.349822 10805 sgd_solver.cpp:106] Iteration 5750, lr = 0.0001
I0405 13:13:08.739143 10805 solver.cpp:242] Iteration 5875 (0.289757 iter/s, 431.396s/125 iter), loss = 6.5365e-06
I0405 13:13:08.739212 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 13:13:08.739223 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.88162e-08 (* 1 = 2.88162e-08 loss)
I0405 13:13:08.739233 10805 sgd_solver.cpp:106] Iteration 5875, lr = 0.0001
I0405 13:20:15.771435 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_6000.caffemodel
I0405 13:20:15.872920 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_6000.solverstate
I0405 13:20:15.948318 10805 solver.cpp:362] Iteration 6000, Testing net (#0)
I0405 13:20:15.948343 10805 net.cpp:723] Ignoring source layer train_data
I0405 13:20:15.948348 10805 net.cpp:723] Ignoring source layer train_label
I0405 13:20:15.948351 10805 net.cpp:723] Ignoring source layer train_transform
I0405 13:20:48.056040 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 13:20:48.056090 10805 solver.cpp:429] Test net output #1: loss_coverage = 9.90965e-10 (* 1 = 9.90965e-10 loss)
I0405 13:20:48.056097 10805 solver.cpp:429] Test net output #2: mAP = 0
I0405 13:20:48.056102 10805 solver.cpp:429] Test net output #3: precision = 0
I0405 13:20:48.056107 10805 solver.cpp:429] Test net output #4: recall = 0
I0405 13:20:51.494134 10805 solver.cpp:242] Iteration 6000 (0.270117 iter/s, 462.762s/125 iter), loss = 6.56073e-06
I0405 13:20:51.494175 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 13:20:51.494184 10805 solver.cpp:261] Train net output #1: loss_coverage = 6.53616e-09 (* 1 = 6.53616e-09 loss)
I0405 13:20:51.494194 10805 sgd_solver.cpp:106] Iteration 6000, lr = 0.0001
I0405 13:28:02.931457 10805 solver.cpp:242] Iteration 6125 (0.289725 iter/s, 431.444s/125 iter), loss = 6.55114e-06
I0405 13:28:02.931571 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 13:28:02.931581 10805 solver.cpp:261] Train net output #1: loss_coverage = 6.03798e-09 (* 1 = 6.03798e-09 loss)
I0405 13:28:02.931593 10805 sgd_solver.cpp:106] Iteration 6125, lr = 0.0001
I0405 13:35:15.846761 10805 solver.cpp:242] Iteration 6250 (0.288736 iter/s, 432.922s/125 iter), loss = 6.53868e-06
I0405 13:35:15.846886 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 13:35:15.846897 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.13647e-10 (* 1 = 2.13647e-10 loss)
I0405 13:35:15.846910 10805 sgd_solver.cpp:106] Iteration 6250, lr = 0.0001
I0405 13:42:28.723361 10805 solver.cpp:242] Iteration 6375 (0.288762 iter/s, 432.883s/125 iter), loss = 6.53853e-06
I0405 13:42:28.723487 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 13:42:28.723498 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.63772e-08 (* 1 = 1.63772e-08 loss)
I0405 13:42:28.723511 10805 sgd_solver.cpp:106] Iteration 6375, lr = 0.0001
I0405 13:49:41.342653 10805 solver.cpp:242] Iteration 6500 (0.288933 iter/s, 432.626s/125 iter), loss = 6.53262e-06
I0405 13:49:41.342808 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 13:49:41.342819 10805 solver.cpp:261] Train net output #1: loss_coverage = 6.70486e-10 (* 1 = 6.70486e-10 loss)
I0405 13:49:41.342833 10805 sgd_solver.cpp:106] Iteration 6500, lr = 0.0001
I0405 13:56:53.701200 10805 solver.cpp:242] Iteration 6625 (0.289108 iter/s, 432.365s/125 iter), loss = 6.53394e-06
I0405 13:56:53.701282 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 13:56:53.701293 10805 solver.cpp:261] Train net output #1: loss_coverage = 7.21061e-10 (* 1 = 7.21061e-10 loss)
I0405 13:56:53.701306 10805 sgd_solver.cpp:106] Iteration 6625, lr = 0.0001
I0405 14:04:06.983222 10805 solver.cpp:242] Iteration 6750 (0.288491 iter/s, 433.289s/125 iter), loss = 6.53011e-06
I0405 14:04:06.983299 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 14:04:06.983310 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.03454e-09 (* 1 = 2.03454e-09 loss)
I0405 14:04:06.983322 10805 sgd_solver.cpp:106] Iteration 6750, lr = 0.0001
I0405 14:11:24.291544 10805 solver.cpp:242] Iteration 6875 (0.285835 iter/s, 437.315s/125 iter), loss = 6.53262e-06
I0405 14:11:24.291635 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 14:11:24.291645 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.9181e-09 (* 1 = 2.9181e-09 loss)
I0405 14:11:24.291658 10805 sgd_solver.cpp:106] Iteration 6875, lr = 0.0001
I0405 14:18:34.001372 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_7000.caffemodel
I0405 14:18:34.100774 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_7000.solverstate
I0405 14:18:34.175684 10805 solver.cpp:362] Iteration 7000, Testing net (#0)
I0405 14:18:34.175709 10805 net.cpp:723] Ignoring source layer train_data
I0405 14:18:34.175714 10805 net.cpp:723] Ignoring source layer train_label
I0405 14:18:34.175717 10805 net.cpp:723] Ignoring source layer train_transform
I0405 14:19:06.588660 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 14:19:06.588714 10805 solver.cpp:429] Test net output #1: loss_coverage = 9.37832e-10 (* 1 = 9.37832e-10 loss)
I0405 14:19:06.588721 10805 solver.cpp:429] Test net output #2: mAP = 0
I0405 14:19:06.588726 10805 solver.cpp:429] Test net output #3: precision = 0
I0405 14:19:06.588731 10805 solver.cpp:429] Test net output #4: recall = 0
I0405 14:19:10.038275 10805 solver.cpp:242] Iteration 7000 (0.268382 iter/s, 465.754s/125 iter), loss = 6.53133e-06
I0405 14:19:10.038319 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 14:19:10.038328 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.88194e-09 (* 1 = 3.88194e-09 loss)
I0405 14:19:10.038341 10805 sgd_solver.cpp:106] Iteration 7000, lr = 0.0001
I0405 14:26:22.938578 10805 solver.cpp:242] Iteration 7125 (0.288746 iter/s, 432.907s/125 iter), loss = 6.55218e-06
I0405 14:26:22.938648 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 14:26:22.938657 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.67935e-09 (* 1 = 2.67935e-09 loss)
I0405 14:26:22.938670 10805 sgd_solver.cpp:106] Iteration 7125, lr = 0.0001
I0405 14:33:35.995492 10805 solver.cpp:242] Iteration 7250 (0.288641 iter/s, 433.063s/125 iter), loss = 6.5495e-06
I0405 14:33:35.995611 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 14:33:35.995622 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.72267e-09 (* 1 = 2.72267e-09 loss)
I0405 14:33:35.995635 10805 sgd_solver.cpp:106] Iteration 7250, lr = 0.0001
I0405 14:40:48.022765 10805 solver.cpp:242] Iteration 7375 (0.289329 iter/s, 432.034s/125 iter), loss = 6.57659e-06
I0405 14:40:48.022873 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 14:40:48.022886 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.83426e-09 (* 1 = 1.83426e-09 loss)
I0405 14:40:48.022898 10805 sgd_solver.cpp:106] Iteration 7375, lr = 0.0001
I0405 14:48:00.853773 10805 solver.cpp:242] Iteration 7500 (0.288792 iter/s, 432.837s/125 iter), loss = 6.53811e-06
I0405 14:48:00.853847 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 14:48:00.853857 10805 solver.cpp:261] Train net output #1: loss_coverage = 8.40182e-10 (* 1 = 8.40182e-10 loss)
I0405 14:48:00.853870 10805 sgd_solver.cpp:106] Iteration 7500, lr = 0.0001
I0405 14:55:13.469900 10805 solver.cpp:242] Iteration 7625 (0.288935 iter/s, 432.623s/125 iter), loss = 6.53125e-06
I0405 14:55:13.469988 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 14:55:13.470000 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.95534e-10 (* 1 = 4.95534e-10 loss)
I0405 14:55:13.470012 10805 sgd_solver.cpp:106] Iteration 7625, lr = 0.0001
I0405 15:02:25.842869 10805 solver.cpp:242] Iteration 7750 (0.289098 iter/s, 432.379s/125 iter), loss = 6.53407e-06
I0405 15:02:25.842934 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 15:02:25.842944 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.31296e-10 (* 1 = 4.31296e-10 loss)
I0405 15:02:25.842955 10805 sgd_solver.cpp:106] Iteration 7750, lr = 0.0001
I0405 15:09:38.447121 10805 solver.cpp:242] Iteration 7875 (0.288943 iter/s, 432.611s/125 iter), loss = 6.54025e-06
I0405 15:09:38.447185 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 15:09:38.447194 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.626e-09 (* 1 = 1.626e-09 loss)
I0405 15:09:38.447206 10805 sgd_solver.cpp:106] Iteration 7875, lr = 0.0001
I0405 15:16:48.164947 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_8000.caffemodel
I0405 15:16:48.267047 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_8000.solverstate
I0405 15:16:48.342933 10805 solver.cpp:362] Iteration 8000, Testing net (#0)
I0405 15:16:48.342960 10805 net.cpp:723] Ignoring source layer train_data
I0405 15:16:48.342965 10805 net.cpp:723] Ignoring source layer train_label
I0405 15:16:48.342968 10805 net.cpp:723] Ignoring source layer train_transform
I0405 15:17:20.217344 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 15:17:20.217465 10805 solver.cpp:429] Test net output #1: loss_coverage = 8.5916e-10 (* 1 = 8.5916e-10 loss)
I0405 15:17:20.217473 10805 solver.cpp:429] Test net output #2: mAP = 0
I0405 15:17:20.217478 10805 solver.cpp:429] Test net output #3: precision = 0
I0405 15:17:20.217483 10805 solver.cpp:429] Test net output #4: recall = 0
I0405 15:17:23.708686 10805 solver.cpp:242] Iteration 8000 (0.268662 iter/s, 465.269s/125 iter), loss = 6.53344e-06
I0405 15:17:23.708739 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 15:17:23.708748 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.89487e-08 (* 1 = 1.89487e-08 loss)
I0405 15:17:23.708761 10805 sgd_solver.cpp:106] Iteration 8000, lr = 0.0001
I0405 15:24:37.453302 10805 solver.cpp:242] Iteration 8125 (0.288184 iter/s, 433.751s/125 iter), loss = 6.59859e-06
I0405 15:24:37.453451 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 15:24:37.453464 10805 solver.cpp:261] Train net output #1: loss_coverage = 6.08028e-10 (* 1 = 6.08028e-10 loss)
I0405 15:24:37.453477 10805 sgd_solver.cpp:106] Iteration 8125, lr = 0.0001
I0405 15:31:51.395311 10805 solver.cpp:242] Iteration 8250 (0.288052 iter/s, 433.949s/125 iter), loss = 6.55596e-06
I0405 15:31:51.395431 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 15:31:51.395442 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.85046e-09 (* 1 = 2.85046e-09 loss)
I0405 15:31:51.395455 10805 sgd_solver.cpp:106] Iteration 8250, lr = 0.0001
I0405 15:39:04.790335 10805 solver.cpp:242] Iteration 8375 (0.288416 iter/s, 433.402s/125 iter), loss = 6.55847e-06
I0405 15:39:04.790473 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 15:39:04.790484 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.44509e-08 (* 1 = 2.44509e-08 loss)
I0405 15:39:04.790496 10805 sgd_solver.cpp:106] Iteration 8375, lr = 0.0001
I0405 15:46:17.802459 10805 solver.cpp:242] Iteration 8500 (0.288671 iter/s, 433.019s/125 iter), loss = 6.53847e-06
I0405 15:46:17.802534 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 15:46:17.802544 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.31485e-09 (* 1 = 1.31485e-09 loss)
I0405 15:46:17.802556 10805 sgd_solver.cpp:106] Iteration 8500, lr = 0.0001
I0405 15:53:31.024358 10805 solver.cpp:242] Iteration 8625 (0.288531 iter/s, 433.229s/125 iter), loss = 6.57641e-06
I0405 15:53:31.024482 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 15:53:31.024492 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.77467e-09 (* 1 = 3.77467e-09 loss)
I0405 15:53:31.024504 10805 sgd_solver.cpp:106] Iteration 8625, lr = 0.0001
I0405 16:00:46.395395 10805 solver.cpp:242] Iteration 8750 (0.287107 iter/s, 435.378s/125 iter), loss = 6.53722e-06
I0405 16:00:46.395481 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 16:00:46.395491 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.86606e-10 (* 1 = 1.86606e-10 loss)
I0405 16:00:46.395506 10805 sgd_solver.cpp:106] Iteration 8750, lr = 0.0001
I0405 16:07:59.358033 10805 solver.cpp:242] Iteration 8875 (0.288704 iter/s, 432.97s/125 iter), loss = 6.55981e-06
I0405 16:07:59.358163 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 16:07:59.358173 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.94767e-09 (* 1 = 3.94767e-09 loss)
I0405 16:07:59.358186 10805 sgd_solver.cpp:106] Iteration 8875, lr = 0.0001
I0405 16:15:08.752776 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_9000.caffemodel
I0405 16:15:08.849377 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_9000.solverstate
I0405 16:15:08.923938 10805 solver.cpp:362] Iteration 9000, Testing net (#0)
I0405 16:15:08.923962 10805 net.cpp:723] Ignoring source layer train_data
I0405 16:15:08.923967 10805 net.cpp:723] Ignoring source layer train_label
I0405 16:15:08.923971 10805 net.cpp:723] Ignoring source layer train_transform
I0405 16:15:40.352072 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 16:15:40.352130 10805 solver.cpp:429] Test net output #1: loss_coverage = 6.79784e-10 (* 1 = 6.79784e-10 loss)
I0405 16:15:40.352136 10805 solver.cpp:429] Test net output #2: mAP = 0
I0405 16:15:40.352141 10805 solver.cpp:429] Test net output #3: precision = 0
I0405 16:15:40.352146 10805 solver.cpp:429] Test net output #4: recall = 0
I0405 16:15:43.853483 10805 solver.cpp:242] Iteration 9000 (0.269105 iter/s, 464.503s/125 iter), loss = 6.53647e-06
I0405 16:15:43.853533 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 16:15:43.853541 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.38432e-08 (* 1 = 1.38432e-08 loss)
I0405 16:15:43.853554 10805 sgd_solver.cpp:106] Iteration 9000, lr = 0.0001
I0405 16:23:00.284315 10805 solver.cpp:242] Iteration 9125 (0.28641 iter/s, 436.438s/125 iter), loss = 6.53467e-06
I0405 16:23:00.284436 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 16:23:00.284448 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.47601e-09 (* 1 = 2.47601e-09 loss)
I0405 16:23:00.284462 10805 sgd_solver.cpp:106] Iteration 9125, lr = 0.0001
I0405 16:30:11.270786 10805 solver.cpp:242] Iteration 9250 (0.290028 iter/s, 430.993s/125 iter), loss = 6.5327e-06
I0405 16:30:11.270933 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 16:30:11.270944 10805 solver.cpp:261] Train net output #1: loss_coverage = 8.07633e-09 (* 1 = 8.07633e-09 loss)
I0405 16:30:11.270958 10805 sgd_solver.cpp:106] Iteration 9250, lr = 0.0001
I0405 16:37:22.073904 10805 solver.cpp:242] Iteration 9375 (0.290151 iter/s, 430.81s/125 iter), loss = 6.53108e-06
I0405 16:37:22.074028 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 16:37:22.074038 10805 solver.cpp:261] Train net output #1: loss_coverage = 6.31343e-09 (* 1 = 6.31343e-09 loss)
I0405 16:37:22.074051 10805 sgd_solver.cpp:106] Iteration 9375, lr = 0.0001
I0405 16:44:32.998489 10805 solver.cpp:242] Iteration 9500 (0.290069 iter/s, 430.931s/125 iter), loss = 6.5371e-06
I0405 16:44:32.998600 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 16:44:32.998610 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.42192e-09 (* 1 = 2.42192e-09 loss)
I0405 16:44:32.998623 10805 sgd_solver.cpp:106] Iteration 9500, lr = 0.0001
I0405 16:51:43.882434 10805 solver.cpp:242] Iteration 9625 (0.290097 iter/s, 430.891s/125 iter), loss = 6.53165e-06
I0405 16:51:43.882555 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 16:51:43.882566 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.12146e-09 (* 1 = 4.12146e-09 loss)
I0405 16:51:43.882578 10805 sgd_solver.cpp:106] Iteration 9625, lr = 0.0001
I0405 16:58:54.465373 10805 solver.cpp:242] Iteration 9750 (0.290299 iter/s, 430.59s/125 iter), loss = 6.54927e-06
I0405 16:58:54.465445 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 16:58:54.465454 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.14076e-09 (* 1 = 3.14076e-09 loss)
I0405 16:58:54.465466 10805 sgd_solver.cpp:106] Iteration 9750, lr = 0.0001
I0405 17:06:05.492002 10805 solver.cpp:242] Iteration 9875 (0.290001 iter/s, 431.034s/125 iter), loss = 6.54414e-06
I0405 17:06:05.492132 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 17:06:05.492143 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.65286e-08 (* 1 = 3.65286e-08 loss)
I0405 17:06:05.492156 10805 sgd_solver.cpp:106] Iteration 9875, lr = 0.0001
I0405 17:13:14.043082 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_10000.caffemodel
I0405 17:13:14.143343 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_10000.solverstate
I0405 17:13:14.218802 10805 solver.cpp:362] Iteration 10000, Testing net (#0)
I0405 17:13:14.218825 10805 net.cpp:723] Ignoring source layer train_data
I0405 17:13:14.218830 10805 net.cpp:723] Ignoring source layer train_label
I0405 17:13:14.218833 10805 net.cpp:723] Ignoring source layer train_transform
I0405 17:13:46.300063 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 17:13:46.300114 10805 solver.cpp:429] Test net output #1: loss_coverage = 7.94946e-10 (* 1 = 7.94946e-10 loss)
I0405 17:13:46.300120 10805 solver.cpp:429] Test net output #2: mAP = 0
I0405 17:13:46.300125 10805 solver.cpp:429] Test net output #3: precision = 0
I0405 17:13:46.300129 10805 solver.cpp:429] Test net output #4: recall = 0
I0405 17:13:49.741511 10805 solver.cpp:242] Iteration 10000 (0.269248 iter/s, 464.257s/125 iter), loss = 6.53009e-06
I0405 17:13:49.741555 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 17:13:49.741565 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.91353e-09 (* 1 = 1.91353e-09 loss)
I0405 17:13:49.741576 10805 sgd_solver.cpp:106] Iteration 10000, lr = 1e-05
I0405 17:21:01.399857 10805 solver.cpp:242] Iteration 10125 (0.289576 iter/s, 431.665s/125 iter), loss = 6.53012e-06
I0405 17:21:01.399933 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 17:21:01.399945 10805 solver.cpp:261] Train net output #1: loss_coverage = 6.519e-10 (* 1 = 6.519e-10 loss)
I0405 17:21:01.399956 10805 sgd_solver.cpp:106] Iteration 10125, lr = 1e-05
I0405 17:28:12.394321 10805 solver.cpp:242] Iteration 10250 (0.290022 iter/s, 431.001s/125 iter), loss = 6.55051e-06
I0405 17:28:12.394424 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 17:28:12.394434 10805 solver.cpp:261] Train net output #1: loss_coverage = 7.0469e-08 (* 1 = 7.0469e-08 loss)
I0405 17:28:12.394446 10805 sgd_solver.cpp:106] Iteration 10250, lr = 1e-05
I0405 17:35:23.871542 10805 solver.cpp:242] Iteration 10375 (0.289698 iter/s, 431.484s/125 iter), loss = 6.53587e-06
I0405 17:35:23.871664 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 17:35:23.871675 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.77525e-10 (* 1 = 2.77525e-10 loss)
I0405 17:35:23.871686 10805 sgd_solver.cpp:106] Iteration 10375, lr = 1e-05
I0405 17:42:35.192267 10805 solver.cpp:242] Iteration 10500 (0.289803 iter/s, 431.328s/125 iter), loss = 6.53416e-06
I0405 17:42:35.192391 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 17:42:35.192402 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.53634e-09 (* 1 = 1.53634e-09 loss)
I0405 17:42:35.192415 10805 sgd_solver.cpp:106] Iteration 10500, lr = 1e-05
I0405 17:49:46.209331 10805 solver.cpp:242] Iteration 10625 (0.290007 iter/s, 431.024s/125 iter), loss = 6.5352e-06
I0405 17:49:46.209404 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 17:49:46.209414 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.09746e-08 (* 1 = 1.09746e-08 loss)
I0405 17:49:46.209425 10805 sgd_solver.cpp:106] Iteration 10625, lr = 1e-05
I0405 17:56:57.297823 10805 solver.cpp:242] Iteration 10750 (0.289959 iter/s, 431.095s/125 iter), loss = 6.53938e-06
I0405 17:56:57.297943 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 17:56:57.297955 10805 solver.cpp:261] Train net output #1: loss_coverage = 5.06762e-08 (* 1 = 5.06762e-08 loss)
I0405 17:56:57.297966 10805 sgd_solver.cpp:106] Iteration 10750, lr = 1e-05
I0405 18:04:08.341339 10805 solver.cpp:242] Iteration 10875 (0.289989 iter/s, 431.05s/125 iter), loss = 6.53267e-06
I0405 18:04:08.341449 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 18:04:08.341459 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.04181e-10 (* 1 = 1.04181e-10 loss)
I0405 18:04:08.341470 10805 sgd_solver.cpp:106] Iteration 10875, lr = 1e-05
I0405 18:11:16.111485 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_11000.caffemodel
I0405 18:11:16.212785 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_11000.solverstate
I0405 18:11:16.293020 10805 solver.cpp:362] Iteration 11000, Testing net (#0)
I0405 18:11:16.293043 10805 net.cpp:723] Ignoring source layer train_data
I0405 18:11:16.293048 10805 net.cpp:723] Ignoring source layer train_label
I0405 18:11:16.293052 10805 net.cpp:723] Ignoring source layer train_transform
I0405 18:11:48.502055 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 18:11:48.502106 10805 solver.cpp:429] Test net output #1: loss_coverage = 8.97159e-10 (* 1 = 8.97159e-10 loss)
I0405 18:11:48.502112 10805 solver.cpp:429] Test net output #2: mAP = 0
I0405 18:11:48.502117 10805 solver.cpp:429] Test net output #3: precision = 0
I0405 18:11:48.502122 10805 solver.cpp:429] Test net output #4: recall = 0
I0405 18:11:51.953225 10805 solver.cpp:242] Iteration 11000 (0.269618 iter/s, 463.619s/125 iter), loss = 6.5322e-06
I0405 18:11:51.953270 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 18:11:51.953279 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.60057e-10 (* 1 = 4.60057e-10 loss)
I0405 18:11:51.953290 10805 sgd_solver.cpp:106] Iteration 11000, lr = 1e-05
I0405 18:19:02.419102 10805 solver.cpp:242] Iteration 11125 (0.290378 iter/s, 430.473s/125 iter), loss = 6.53187e-06
I0405 18:19:02.419205 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 18:19:02.419215 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.27446e-10 (* 1 = 4.27446e-10 loss)
I0405 18:19:02.419229 10805 sgd_solver.cpp:106] Iteration 11125, lr = 1e-05
I0405 18:26:13.268059 10805 solver.cpp:242] Iteration 11250 (0.29012 iter/s, 430.856s/125 iter), loss = 6.53161e-06
I0405 18:26:13.268128 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 18:26:13.268137 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.02111e-09 (* 1 = 2.02111e-09 loss)
I0405 18:26:13.268149 10805 sgd_solver.cpp:106] Iteration 11250, lr = 1e-05
I0405 18:33:24.038714 10805 solver.cpp:242] Iteration 11375 (0.290173 iter/s, 430.777s/125 iter), loss = 6.53077e-06
I0405 18:33:24.038832 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 18:33:24.038842 10805 solver.cpp:261] Train net output #1: loss_coverage = 7.03462e-10 (* 1 = 7.03462e-10 loss)
I0405 18:33:24.038854 10805 sgd_solver.cpp:106] Iteration 11375, lr = 1e-05
I0405 18:40:34.435117 10805 solver.cpp:242] Iteration 11500 (0.290425 iter/s, 430.403s/125 iter), loss = 6.53655e-06
I0405 18:40:34.435235 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 18:40:34.435245 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.4421e-09 (* 1 = 3.4421e-09 loss)
I0405 18:40:34.435257 10805 sgd_solver.cpp:106] Iteration 11500, lr = 1e-05
I0405 18:47:45.317850 10805 solver.cpp:242] Iteration 11625 (0.290098 iter/s, 430.889s/125 iter), loss = 6.55366e-06
I0405 18:47:45.317919 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 18:47:45.317929 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.95006e-08 (* 1 = 4.95006e-08 loss)
I0405 18:47:45.317939 10805 sgd_solver.cpp:106] Iteration 11625, lr = 1e-05
I0405 18:54:56.855602 10805 solver.cpp:242] Iteration 11750 (0.289657 iter/s, 431.544s/125 iter), loss = 6.54997e-06
I0405 18:54:56.855729 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 18:54:56.855741 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.73585e-09 (* 1 = 1.73585e-09 loss)
I0405 18:54:56.855752 10805 sgd_solver.cpp:106] Iteration 11750, lr = 1e-05
I0405 19:02:07.659270 10805 solver.cpp:242] Iteration 11875 (0.290151 iter/s, 430.81s/125 iter), loss = 6.53448e-06
I0405 19:02:07.659379 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 19:02:07.659389 10805 solver.cpp:261] Train net output #1: loss_coverage = 5.70957e-09 (* 1 = 5.70957e-09 loss)
I0405 19:02:07.659401 10805 sgd_solver.cpp:106] Iteration 11875, lr = 1e-05
I0405 19:09:15.429178 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_12000.caffemodel
I0405 19:09:15.529717 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_12000.solverstate
I0405 19:09:15.604984 10805 solver.cpp:362] Iteration 12000, Testing net (#0)
I0405 19:09:15.605010 10805 net.cpp:723] Ignoring source layer train_data
I0405 19:09:15.605013 10805 net.cpp:723] Ignoring source layer train_label
I0405 19:09:15.605017 10805 net.cpp:723] Ignoring source layer train_transform
I0405 19:09:47.765219 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 19:09:47.765269 10805 solver.cpp:429] Test net output #1: loss_coverage = 7.40554e-10 (* 1 = 7.40554e-10 loss)
I0405 19:09:47.765276 10805 solver.cpp:429] Test net output #2: mAP = 0
I0405 19:09:47.765280 10805 solver.cpp:429] Test net output #3: precision = 0
I0405 19:09:47.765285 10805 solver.cpp:429] Test net output #4: recall = 0
I0405 19:09:51.227495 10805 solver.cpp:242] Iteration 12000 (0.269643 iter/s, 463.576s/125 iter), loss = 6.54031e-06
I0405 19:09:51.227541 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 19:09:51.227551 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.18253e-08 (* 1 = 4.18253e-08 loss)
I0405 19:09:51.227563 10805 sgd_solver.cpp:106] Iteration 12000, lr = 1e-05
I0405 19:17:02.810278 10805 solver.cpp:242] Iteration 12125 (0.289627 iter/s, 431.59s/125 iter), loss = 6.53782e-06
I0405 19:17:02.810374 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 19:17:02.810384 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.73662e-09 (* 1 = 1.73662e-09 loss)
I0405 19:17:02.810395 10805 sgd_solver.cpp:106] Iteration 12125, lr = 1e-05
I0405 19:24:12.859961 10805 solver.cpp:242] Iteration 12250 (0.29066 iter/s, 430.056s/125 iter), loss = 6.5312e-06
I0405 19:24:12.860040 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 19:24:12.860050 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.92484e-09 (* 1 = 2.92484e-09 loss)
I0405 19:24:12.860062 10805 sgd_solver.cpp:106] Iteration 12250, lr = 1e-05
I0405 19:31:24.161813 10805 solver.cpp:242] Iteration 12375 (0.289816 iter/s, 431.309s/125 iter), loss = 6.54052e-06
I0405 19:31:24.161885 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 19:31:24.161895 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.0363e-08 (* 1 = 3.0363e-08 loss)
I0405 19:31:24.161907 10805 sgd_solver.cpp:106] Iteration 12375, lr = 1e-05
I0405 19:38:35.703351 10805 solver.cpp:242] Iteration 12500 (0.289655 iter/s, 431.548s/125 iter), loss = 6.53323e-06
I0405 19:38:35.703415 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 19:38:35.703424 10805 solver.cpp:261] Train net output #1: loss_coverage = 8.97842e-09 (* 1 = 8.97842e-09 loss)
I0405 19:38:35.703436 10805 sgd_solver.cpp:106] Iteration 12500, lr = 1e-05
I0405 19:45:47.370061 10805 solver.cpp:242] Iteration 12625 (0.289571 iter/s, 431.673s/125 iter), loss = 6.54233e-06
I0405 19:45:47.370172 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 19:45:47.370182 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.7496e-08 (* 1 = 4.7496e-08 loss)
I0405 19:45:47.370194 10805 sgd_solver.cpp:106] Iteration 12625, lr = 1e-05
I0405 19:52:58.419385 10805 solver.cpp:242] Iteration 12750 (0.289985 iter/s, 431.056s/125 iter), loss = 6.54822e-06
I0405 19:52:58.419452 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 19:52:58.419461 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.70433e-08 (* 1 = 4.70433e-08 loss)
I0405 19:52:58.419472 10805 sgd_solver.cpp:106] Iteration 12750, lr = 1e-05
I0405 20:00:09.082391 10805 solver.cpp:242] Iteration 12875 (0.290246 iter/s, 430.67s/125 iter), loss = 6.53438e-06
I0405 20:00:09.082491 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 20:00:09.082504 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.74511e-09 (* 1 = 2.74511e-09 loss)
I0405 20:00:09.082515 10805 sgd_solver.cpp:106] Iteration 12875, lr = 1e-05
I0405 20:07:16.278992 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_13000.caffemodel
I0405 20:07:16.380368 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_13000.solverstate
I0405 20:07:16.455679 10805 solver.cpp:362] Iteration 13000, Testing net (#0)
I0405 20:07:16.455703 10805 net.cpp:723] Ignoring source layer train_data
I0405 20:07:16.455708 10805 net.cpp:723] Ignoring source layer train_label
I0405 20:07:16.455713 10805 net.cpp:723] Ignoring source layer train_transform
I0405 20:07:48.553112 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 20:07:48.553160 10805 solver.cpp:429] Test net output #1: loss_coverage = 8.64785e-10 (* 1 = 8.64785e-10 loss)
I0405 20:07:48.553166 10805 solver.cpp:429] Test net output #2: mAP = 0
I0405 20:07:48.553170 10805 solver.cpp:429] Test net output #3: precision = 0
I0405 20:07:48.553175 10805 solver.cpp:429] Test net output #4: recall = 0
I0405 20:07:51.969733 10805 solver.cpp:242] Iteration 13000 (0.27004 iter/s, 462.895s/125 iter), loss = 6.53616e-06
I0405 20:07:51.969777 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 20:07:51.969786 10805 solver.cpp:261] Train net output #1: loss_coverage = 6.14839e-09 (* 1 = 6.14839e-09 loss)
I0405 20:07:51.969797 10805 sgd_solver.cpp:106] Iteration 13000, lr = 1e-05
I0405 20:15:03.220091 10805 solver.cpp:242] Iteration 13125 (0.28985 iter/s, 431.257s/125 iter), loss = 6.53928e-06
I0405 20:15:03.220187 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 20:15:03.220199 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.28714e-08 (* 1 = 2.28714e-08 loss)
I0405 20:15:03.220211 10805 sgd_solver.cpp:106] Iteration 13125, lr = 1e-05
I0405 20:22:14.687537 10805 solver.cpp:242] Iteration 13250 (0.289704 iter/s, 431.474s/125 iter), loss = 6.53381e-06
I0405 20:22:14.687613 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 20:22:14.687623 10805 solver.cpp:261] Train net output #1: loss_coverage = 5.57287e-10 (* 1 = 5.57287e-10 loss)
I0405 20:22:14.687636 10805 sgd_solver.cpp:106] Iteration 13250, lr = 1e-05
I0405 20:29:25.786762 10805 solver.cpp:242] Iteration 13375 (0.289952 iter/s, 431.106s/125 iter), loss = 6.52893e-06
I0405 20:29:25.786828 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 20:29:25.786839 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.91734e-10 (* 1 = 3.91734e-10 loss)
I0405 20:29:25.786849 10805 sgd_solver.cpp:106] Iteration 13375, lr = 1e-05
I0405 20:36:37.062889 10805 solver.cpp:242] Iteration 13500 (0.289833 iter/s, 431.283s/125 iter), loss = 6.53798e-06
I0405 20:36:37.063000 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 20:36:37.063010 10805 solver.cpp:261] Train net output #1: loss_coverage = 9.44422e-09 (* 1 = 9.44422e-09 loss)
I0405 20:36:37.063024 10805 sgd_solver.cpp:106] Iteration 13500, lr = 1e-05
I0405 20:43:48.730873 10805 solver.cpp:242] Iteration 13625 (0.28957 iter/s, 431.675s/125 iter), loss = 6.54076e-06
I0405 20:43:48.730937 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 20:43:48.730947 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.1546e-09 (* 1 = 1.1546e-09 loss)
I0405 20:43:48.730958 10805 sgd_solver.cpp:106] Iteration 13625, lr = 1e-05
I0405 20:50:59.466780 10805 solver.cpp:242] Iteration 13750 (0.290196 iter/s, 430.743s/125 iter), loss = 6.53555e-06
I0405 20:50:59.466845 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 20:50:59.466855 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.50192e-08 (* 1 = 2.50192e-08 loss)
I0405 20:50:59.466866 10805 sgd_solver.cpp:106] Iteration 13750, lr = 1e-05
I0405 20:58:10.594257 10805 solver.cpp:242] Iteration 13875 (0.289933 iter/s, 431.134s/125 iter), loss = 6.53158e-06
I0405 20:58:10.594324 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 20:58:10.594334 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.86142e-10 (* 1 = 1.86142e-10 loss)
I0405 20:58:10.594347 10805 sgd_solver.cpp:106] Iteration 13875, lr = 1e-05
I0405 21:05:18.375018 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_14000.caffemodel
I0405 21:05:18.470513 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_14000.solverstate
I0405 21:05:18.545060 10805 solver.cpp:362] Iteration 14000, Testing net (#0)
I0405 21:05:18.545083 10805 net.cpp:723] Ignoring source layer train_data
I0405 21:05:18.545089 10805 net.cpp:723] Ignoring source layer train_label
I0405 21:05:18.545091 10805 net.cpp:723] Ignoring source layer train_transform
I0405 21:05:50.216320 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 21:05:50.216364 10805 solver.cpp:429] Test net output #1: loss_coverage = 9.99399e-10 (* 1 = 9.99399e-10 loss)
I0405 21:05:50.216372 10805 solver.cpp:429] Test net output #2: mAP = 0
I0405 21:05:50.216375 10805 solver.cpp:429] Test net output #3: precision = 0
I0405 21:05:50.216380 10805 solver.cpp:429] Test net output #4: recall = 0
I0405 21:05:53.674159 10805 solver.cpp:242] Iteration 14000 (0.269928 iter/s, 463.087s/125 iter), loss = 6.53026e-06
I0405 21:05:53.674199 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 21:05:53.674208 10805 solver.cpp:261] Train net output #1: loss_coverage = 7.59652e-10 (* 1 = 7.59652e-10 loss)
I0405 21:05:53.674219 10805 sgd_solver.cpp:106] Iteration 14000, lr = 1e-05
I0405 21:13:05.276408 10805 solver.cpp:242] Iteration 14125 (0.289614 iter/s, 431.609s/125 iter), loss = 6.5337e-06
I0405 21:13:05.276547 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 21:13:05.276558 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.31766e-09 (* 1 = 1.31766e-09 loss)
I0405 21:13:05.276571 10805 sgd_solver.cpp:106] Iteration 14125, lr = 1e-05
I0405 21:20:16.879532 10805 solver.cpp:242] Iteration 14250 (0.289613 iter/s, 431.61s/125 iter), loss = 6.5353e-06
I0405 21:20:16.879611 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 21:20:16.879621 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.58337e-10 (* 1 = 2.58337e-10 loss)
I0405 21:20:16.879633 10805 sgd_solver.cpp:106] Iteration 14250, lr = 1e-05
I0405 21:27:27.612113 10805 solver.cpp:242] Iteration 14375 (0.290199 iter/s, 430.739s/125 iter), loss = 6.52916e-06
I0405 21:27:27.612231 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 21:27:27.612241 10805 solver.cpp:261] Train net output #1: loss_coverage = 9.28944e-10 (* 1 = 9.28944e-10 loss)
I0405 21:27:27.612254 10805 sgd_solver.cpp:106] Iteration 14375, lr = 1e-05
I0405 21:34:38.069200 10805 solver.cpp:242] Iteration 14500 (0.290384 iter/s, 430.464s/125 iter), loss = 6.53204e-06
I0405 21:34:38.069319 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 21:34:38.069329 10805 solver.cpp:261] Train net output #1: loss_coverage = 7.19795e-09 (* 1 = 7.19795e-09 loss)
I0405 21:34:38.069340 10805 sgd_solver.cpp:106] Iteration 14500, lr = 1e-05
I0405 21:41:48.916560 10805 solver.cpp:242] Iteration 14625 (0.290121 iter/s, 430.854s/125 iter), loss = 6.53755e-06
I0405 21:41:48.916663 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 21:41:48.916674 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.24705e-09 (* 1 = 2.24705e-09 loss)
I0405 21:41:48.916685 10805 sgd_solver.cpp:106] Iteration 14625, lr = 1e-05
I0405 21:48:59.926816 10805 solver.cpp:242] Iteration 14750 (0.290012 iter/s, 431.017s/125 iter), loss = 6.53517e-06
I0405 21:48:59.926885 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 21:48:59.926894 10805 solver.cpp:261] Train net output #1: loss_coverage = 5.04833e-09 (* 1 = 5.04833e-09 loss)
I0405 21:48:59.926905 10805 sgd_solver.cpp:106] Iteration 14750, lr = 1e-05
I0405 21:56:11.146543 10805 solver.cpp:242] Iteration 14875 (0.289871 iter/s, 431.227s/125 iter), loss = 6.54493e-06
I0405 21:56:11.146613 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 21:56:11.146622 10805 solver.cpp:261] Train net output #1: loss_coverage = 7.48001e-08 (* 1 = 7.48001e-08 loss)
I0405 21:56:11.146634 10805 sgd_solver.cpp:106] Iteration 14875, lr = 1e-05
I0405 22:03:18.722234 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_15000.caffemodel
I0405 22:03:18.818084 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_15000.solverstate
I0405 22:03:18.896733 10805 solver.cpp:362] Iteration 15000, Testing net (#0)
I0405 22:03:18.896756 10805 net.cpp:723] Ignoring source layer train_data
I0405 22:03:18.896760 10805 net.cpp:723] Ignoring source layer train_label
I0405 22:03:18.896764 10805 net.cpp:723] Ignoring source layer train_transform
I0405 22:03:50.950677 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 22:03:50.950743 10805 solver.cpp:429] Test net output #1: loss_coverage = 7.93895e-10 (* 1 = 7.93895e-10 loss)
I0405 22:03:50.950750 10805 solver.cpp:429] Test net output #2: mAP = 0
I0405 22:03:50.950755 10805 solver.cpp:429] Test net output #3: precision = 0
I0405 22:03:50.950759 10805 solver.cpp:429] Test net output #4: recall = 0
I0405 22:03:54.409586 10805 solver.cpp:242] Iteration 15000 (0.269821 iter/s, 463.27s/125 iter), loss = 6.53569e-06
I0405 22:03:54.409636 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 22:03:54.409646 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.77051e-08 (* 1 = 1.77051e-08 loss)
I0405 22:03:54.409658 10805 sgd_solver.cpp:106] Iteration 15000, lr = 1e-05
I0405 22:11:05.130659 10805 solver.cpp:242] Iteration 15125 (0.290206 iter/s, 430.728s/125 iter), loss = 6.53478e-06
I0405 22:11:05.130769 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 22:11:05.130779 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.11589e-09 (* 1 = 1.11589e-09 loss)
I0405 22:11:05.130791 10805 sgd_solver.cpp:106] Iteration 15125, lr = 1e-05
I0405 22:18:16.397914 10805 solver.cpp:242] Iteration 15250 (0.289839 iter/s, 431.274s/125 iter), loss = 6.54103e-06
I0405 22:18:16.398020 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 22:18:16.398030 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.30579e-08 (* 1 = 1.30579e-08 loss)
I0405 22:18:16.398041 10805 sgd_solver.cpp:106] Iteration 15250, lr = 1e-05
I0405 22:25:26.645591 10805 solver.cpp:242] Iteration 15375 (0.290526 iter/s, 430.254s/125 iter), loss = 6.52928e-06
I0405 22:25:26.645659 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 22:25:26.645668 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.7124e-10 (* 1 = 2.7124e-10 loss)
I0405 22:25:26.645680 10805 sgd_solver.cpp:106] Iteration 15375, lr = 1e-05
I0405 22:32:37.773743 10805 solver.cpp:242] Iteration 15500 (0.289932 iter/s, 431.135s/125 iter), loss = 6.53258e-06
I0405 22:32:37.773852 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 22:32:37.773862 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.41431e-09 (* 1 = 3.41431e-09 loss)
I0405 22:32:37.773875 10805 sgd_solver.cpp:106] Iteration 15500, lr = 1e-05
I0405 22:39:48.391383 10805 solver.cpp:242] Iteration 15625 (0.290276 iter/s, 430.624s/125 iter), loss = 6.55393e-06
I0405 22:39:48.391496 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 22:39:48.391507 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.55712e-09 (* 1 = 2.55712e-09 loss)
I0405 22:39:48.391518 10805 sgd_solver.cpp:106] Iteration 15625, lr = 1e-05
I0405 22:46:59.518934 10805 solver.cpp:242] Iteration 15750 (0.289933 iter/s, 431.134s/125 iter), loss = 6.57201e-06
I0405 22:46:59.519006 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 22:46:59.519016 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.59544e-09 (* 1 = 1.59544e-09 loss)
I0405 22:46:59.519027 10805 sgd_solver.cpp:106] Iteration 15750, lr = 1e-05
I0405 22:54:10.103636 10805 solver.cpp:242] Iteration 15875 (0.290298 iter/s, 430.591s/125 iter), loss = 6.53106e-06
I0405 22:54:10.103700 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 22:54:10.103709 10805 solver.cpp:261] Train net output #1: loss_coverage = 5.03537e-10 (* 1 = 5.03537e-10 loss)
I0405 22:54:10.103720 10805 sgd_solver.cpp:106] Iteration 15875, lr = 1e-05
I0405 23:01:17.709899 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_16000.caffemodel
I0405 23:01:17.810057 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_16000.solverstate
I0405 23:01:17.885208 10805 solver.cpp:362] Iteration 16000, Testing net (#0)
I0405 23:01:17.885232 10805 net.cpp:723] Ignoring source layer train_data
I0405 23:01:17.885237 10805 net.cpp:723] Ignoring source layer train_label
I0405 23:01:17.885241 10805 net.cpp:723] Ignoring source layer train_transform
I0405 23:01:49.840168 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 23:01:49.840287 10805 solver.cpp:429] Test net output #1: loss_coverage = 9.58893e-10 (* 1 = 9.58893e-10 loss)
I0405 23:01:49.840296 10805 solver.cpp:429] Test net output #2: mAP = 0
I0405 23:01:49.840301 10805 solver.cpp:429] Test net output #3: precision = 0
I0405 23:01:49.840306 10805 solver.cpp:429] Test net output #4: recall = 0
I0405 23:01:53.301218 10805 solver.cpp:242] Iteration 16000 (0.269859 iter/s, 463.205s/125 iter), loss = 6.54146e-06
I0405 23:01:53.301260 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 23:01:53.301270 10805 solver.cpp:261] Train net output #1: loss_coverage = 5.1379e-10 (* 1 = 5.1379e-10 loss)
I0405 23:01:53.301281 10805 sgd_solver.cpp:106] Iteration 16000, lr = 1e-05
I0405 23:09:04.424407 10805 solver.cpp:242] Iteration 16125 (0.289936 iter/s, 431.13s/125 iter), loss = 6.52988e-06
I0405 23:09:04.424531 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 23:09:04.424542 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.13459e-09 (* 1 = 1.13459e-09 loss)
I0405 23:09:04.424556 10805 sgd_solver.cpp:106] Iteration 16125, lr = 1e-05
I0405 23:16:15.687135 10805 solver.cpp:242] Iteration 16250 (0.289842 iter/s, 431.27s/125 iter), loss = 6.54228e-06
I0405 23:16:15.687201 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 23:16:15.687209 10805 solver.cpp:261] Train net output #1: loss_coverage = 7.25318e-08 (* 1 = 7.25318e-08 loss)
I0405 23:16:15.687222 10805 sgd_solver.cpp:106] Iteration 16250, lr = 1e-05
I0405 23:23:26.823479 10805 solver.cpp:242] Iteration 16375 (0.289927 iter/s, 431.143s/125 iter), loss = 6.53411e-06
I0405 23:23:26.823554 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 23:23:26.823562 10805 solver.cpp:261] Train net output #1: loss_coverage = 9.07647e-09 (* 1 = 9.07647e-09 loss)
I0405 23:23:26.823575 10805 sgd_solver.cpp:106] Iteration 16375, lr = 1e-05
I0405 23:30:38.554373 10805 solver.cpp:242] Iteration 16500 (0.289528 iter/s, 431.738s/125 iter), loss = 6.53722e-06
I0405 23:30:38.554486 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 23:30:38.554497 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.5197e-08 (* 1 = 3.5197e-08 loss)
I0405 23:30:38.554508 10805 sgd_solver.cpp:106] Iteration 16500, lr = 1e-05
I0405 23:37:49.255239 10805 solver.cpp:242] Iteration 16625 (0.29022 iter/s, 430.708s/125 iter), loss = 6.5334e-06
I0405 23:37:49.255304 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 23:37:49.255314 10805 solver.cpp:261] Train net output #1: loss_coverage = 5.76891e-10 (* 1 = 5.76891e-10 loss)
I0405 23:37:49.255326 10805 sgd_solver.cpp:106] Iteration 16625, lr = 1e-05
I0405 23:45:00.381798 10805 solver.cpp:242] Iteration 16750 (0.289934 iter/s, 431.133s/125 iter), loss = 6.53718e-06
I0405 23:45:00.381925 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 23:45:00.381937 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.86784e-09 (* 1 = 3.86784e-09 loss)
I0405 23:45:00.381950 10805 sgd_solver.cpp:106] Iteration 16750, lr = 1e-05
I0405 23:52:11.475481 10805 solver.cpp:242] Iteration 16875 (0.289956 iter/s, 431.101s/125 iter), loss = 6.53096e-06
I0405 23:52:11.475600 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 23:52:11.475610 10805 solver.cpp:261] Train net output #1: loss_coverage = 7.7028e-10 (* 1 = 7.7028e-10 loss)
I0405 23:52:11.475623 10805 sgd_solver.cpp:106] Iteration 16875, lr = 1e-05
I0405 23:59:19.631244 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_17000.caffemodel
I0405 23:59:19.726680 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_17000.solverstate
I0405 23:59:19.801009 10805 solver.cpp:362] Iteration 17000, Testing net (#0)
I0405 23:59:19.801031 10805 net.cpp:723] Ignoring source layer train_data
I0405 23:59:19.801036 10805 net.cpp:723] Ignoring source layer train_label
I0405 23:59:19.801040 10805 net.cpp:723] Ignoring source layer train_transform
I0405 23:59:51.932415 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 23:59:51.932493 10805 solver.cpp:429] Test net output #1: loss_coverage = 9.55851e-10 (* 1 = 9.55851e-10 loss)
I0405 23:59:51.932500 10805 solver.cpp:429] Test net output #2: mAP = 0
I0405 23:59:51.932505 10805 solver.cpp:429] Test net output #3: precision = 0
I0405 23:59:51.932509 10805 solver.cpp:429] Test net output #4: recall = 0
I0405 23:59:55.335939 10805 solver.cpp:242] Iteration 17000 (0.269473 iter/s, 463.868s/125 iter), loss = 6.53262e-06
I0405 23:59:55.335983 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0405 23:59:55.335991 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.50681e-08 (* 1 = 1.50681e-08 loss)
I0405 23:59:55.336002 10805 sgd_solver.cpp:106] Iteration 17000, lr = 1e-05
I0406 00:07:06.331460 10805 solver.cpp:242] Iteration 17125 (0.290022 iter/s, 431.002s/125 iter), loss = 6.53069e-06
I0406 00:07:06.331542 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 00:07:06.331552 10805 solver.cpp:261] Train net output #1: loss_coverage = 6.71435e-09 (* 1 = 6.71435e-09 loss)
I0406 00:07:06.331563 10805 sgd_solver.cpp:106] Iteration 17125, lr = 1e-05
I0406 00:14:17.465947 10805 solver.cpp:242] Iteration 17250 (0.289928 iter/s, 431.141s/125 iter), loss = 6.55055e-06
I0406 00:14:17.466024 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 00:14:17.466034 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.11738e-07 (* 1 = 1.11738e-07 loss)
I0406 00:14:17.466047 10805 sgd_solver.cpp:106] Iteration 17250, lr = 1e-05
I0406 00:21:29.730993 10805 solver.cpp:242] Iteration 17375 (0.28917 iter/s, 432.272s/125 iter), loss = 6.53505e-06
I0406 00:21:29.731106 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 00:21:29.731117 10805 solver.cpp:261] Train net output #1: loss_coverage = 7.78526e-09 (* 1 = 7.78526e-09 loss)
I0406 00:21:29.731128 10805 sgd_solver.cpp:106] Iteration 17375, lr = 1e-05
I0406 00:28:41.763342 10805 solver.cpp:242] Iteration 17500 (0.289326 iter/s, 432.039s/125 iter), loss = 6.53433e-06
I0406 00:28:41.763424 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 00:28:41.763435 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.01512e-09 (* 1 = 4.01512e-09 loss)
I0406 00:28:41.763448 10805 sgd_solver.cpp:106] Iteration 17500, lr = 1e-05
I0406 00:35:54.273874 10805 solver.cpp:242] Iteration 17625 (0.289006 iter/s, 432.517s/125 iter), loss = 6.53298e-06
I0406 00:35:54.273977 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 00:35:54.273993 10805 solver.cpp:261] Train net output #1: loss_coverage = 7.15823e-09 (* 1 = 7.15823e-09 loss)
I0406 00:35:54.274026 10805 sgd_solver.cpp:106] Iteration 17625, lr = 1e-05
I0406 00:43:07.046227 10805 solver.cpp:242] Iteration 17750 (0.288831 iter/s, 432.779s/125 iter), loss = 6.532e-06
I0406 00:43:07.046372 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 00:43:07.046385 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.13902e-09 (* 1 = 1.13902e-09 loss)
I0406 00:43:07.046397 10805 sgd_solver.cpp:106] Iteration 17750, lr = 1e-05
I0406 00:50:19.699136 10805 solver.cpp:242] Iteration 17875 (0.288911 iter/s, 432.66s/125 iter), loss = 6.53684e-06
I0406 00:50:19.699245 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 00:50:19.699256 10805 solver.cpp:261] Train net output #1: loss_coverage = 7.4092e-10 (* 1 = 7.4092e-10 loss)
I0406 00:50:19.699270 10805 sgd_solver.cpp:106] Iteration 17875, lr = 1e-05
I0406 00:57:29.018600 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_18000.caffemodel
I0406 00:57:29.114745 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_18000.solverstate
I0406 00:57:29.193259 10805 solver.cpp:362] Iteration 18000, Testing net (#0)
I0406 00:57:29.193284 10805 net.cpp:723] Ignoring source layer train_data
I0406 00:57:29.193289 10805 net.cpp:723] Ignoring source layer train_label
I0406 00:57:29.193291 10805 net.cpp:723] Ignoring source layer train_transform
I0406 00:58:01.496613 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 00:58:01.496702 10805 solver.cpp:429] Test net output #1: loss_coverage = 1.01064e-09 (* 1 = 1.01064e-09 loss)
I0406 00:58:01.496709 10805 solver.cpp:429] Test net output #2: mAP = 0
I0406 00:58:01.496714 10805 solver.cpp:429] Test net output #3: precision = 0
I0406 00:58:01.496718 10805 solver.cpp:429] Test net output #4: recall = 0
I0406 00:58:04.937134 10805 solver.cpp:242] Iteration 18000 (0.268675 iter/s, 465.246s/125 iter), loss = 6.53425e-06
I0406 00:58:04.937178 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 00:58:04.937187 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.58634e-09 (* 1 = 1.58634e-09 loss)
I0406 00:58:04.937198 10805 sgd_solver.cpp:106] Iteration 18000, lr = 1e-05
I0406 01:05:17.488838 10805 solver.cpp:242] Iteration 18125 (0.288978 iter/s, 432.559s/125 iter), loss = 6.54012e-06
I0406 01:05:17.488930 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 01:05:17.488941 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.8474e-09 (* 1 = 2.8474e-09 loss)
I0406 01:05:17.488953 10805 sgd_solver.cpp:106] Iteration 18125, lr = 1e-05
I0406 01:12:31.386785 10805 solver.cpp:242] Iteration 18250 (0.288081 iter/s, 433.905s/125 iter), loss = 6.53201e-06
I0406 01:12:31.386863 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 01:12:31.386874 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.79172e-09 (* 1 = 2.79172e-09 loss)
I0406 01:12:31.386888 10805 sgd_solver.cpp:106] Iteration 18250, lr = 1e-05
I0406 01:19:45.356806 10805 solver.cpp:242] Iteration 18375 (0.288034 iter/s, 433.977s/125 iter), loss = 6.53978e-06
I0406 01:19:45.356950 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 01:19:45.356961 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.4576e-08 (* 1 = 1.4576e-08 loss)
I0406 01:19:45.356973 10805 sgd_solver.cpp:106] Iteration 18375, lr = 1e-05
I0406 01:26:59.322667 10805 solver.cpp:242] Iteration 18500 (0.288036 iter/s, 433.973s/125 iter), loss = 6.54023e-06
I0406 01:26:59.322751 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 01:26:59.322762 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.19088e-09 (* 1 = 1.19088e-09 loss)
I0406 01:26:59.322775 10805 sgd_solver.cpp:106] Iteration 18500, lr = 1e-05
I0406 01:34:12.375062 10805 solver.cpp:242] Iteration 18625 (0.288644 iter/s, 433.059s/125 iter), loss = 6.53389e-06
I0406 01:34:12.375138 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 01:34:12.375149 10805 solver.cpp:261] Train net output #1: loss_coverage = 9.31912e-09 (* 1 = 9.31912e-09 loss)
I0406 01:34:12.375160 10805 sgd_solver.cpp:106] Iteration 18625, lr = 1e-05
I0406 01:41:25.439865 10805 solver.cpp:242] Iteration 18750 (0.288636 iter/s, 433.071s/125 iter), loss = 6.53685e-06
I0406 01:41:25.439939 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 01:41:25.439949 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.59499e-08 (* 1 = 1.59499e-08 loss)
I0406 01:41:25.439962 10805 sgd_solver.cpp:106] Iteration 18750, lr = 1e-05
I0406 01:48:37.509914 10805 solver.cpp:242] Iteration 18875 (0.2893 iter/s, 432.077s/125 iter), loss = 6.53692e-06
I0406 01:48:37.509990 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 01:48:37.510000 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.68849e-08 (* 1 = 2.68849e-08 loss)
I0406 01:48:37.510012 10805 sgd_solver.cpp:106] Iteration 18875, lr = 1e-05
I0406 01:55:46.887814 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_19000.caffemodel
I0406 01:55:46.984580 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_19000.solverstate
I0406 01:55:47.058825 10805 solver.cpp:362] Iteration 19000, Testing net (#0)
I0406 01:55:47.058851 10805 net.cpp:723] Ignoring source layer train_data
I0406 01:55:47.058856 10805 net.cpp:723] Ignoring source layer train_label
I0406 01:55:47.058859 10805 net.cpp:723] Ignoring source layer train_transform
I0406 01:56:19.394819 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 01:56:19.394865 10805 solver.cpp:429] Test net output #1: loss_coverage = 9.43732e-10 (* 1 = 9.43732e-10 loss)
I0406 01:56:19.394870 10805 solver.cpp:429] Test net output #2: mAP = 0
I0406 01:56:19.394876 10805 solver.cpp:429] Test net output #3: precision = 0
I0406 01:56:19.394879 10805 solver.cpp:429] Test net output #4: recall = 0
I0406 01:56:22.855774 10805 solver.cpp:242] Iteration 19000 (0.268613 iter/s, 465.353s/125 iter), loss = 6.53291e-06
I0406 01:56:22.855820 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 01:56:22.855829 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.84455e-08 (* 1 = 1.84455e-08 loss)
I0406 01:56:22.855841 10805 sgd_solver.cpp:106] Iteration 19000, lr = 1e-05
I0406 02:03:35.912643 10805 solver.cpp:242] Iteration 19125 (0.288641 iter/s, 433.064s/125 iter), loss = 6.53796e-06
I0406 02:03:35.912721 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 02:03:35.912732 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.06176e-08 (* 1 = 2.06176e-08 loss)
I0406 02:03:35.912745 10805 sgd_solver.cpp:106] Iteration 19125, lr = 1e-05
I0406 02:10:48.564821 10805 solver.cpp:242] Iteration 19250 (0.288911 iter/s, 432.659s/125 iter), loss = 6.53467e-06
I0406 02:10:48.564944 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 02:10:48.564954 10805 solver.cpp:261] Train net output #1: loss_coverage = 8.85871e-09 (* 1 = 8.85871e-09 loss)
I0406 02:10:48.564967 10805 sgd_solver.cpp:106] Iteration 19250, lr = 1e-05
I0406 02:18:00.482892 10805 solver.cpp:242] Iteration 19375 (0.289402 iter/s, 431.925s/125 iter), loss = 6.5342e-06
I0406 02:18:00.482969 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 02:18:00.482980 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.04971e-08 (* 1 = 1.04971e-08 loss)
I0406 02:18:00.482991 10805 sgd_solver.cpp:106] Iteration 19375, lr = 1e-05
I0406 02:25:12.857139 10805 solver.cpp:242] Iteration 19500 (0.289097 iter/s, 432.381s/125 iter), loss = 6.54253e-06
I0406 02:25:12.857216 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 02:25:12.857226 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.39168e-09 (* 1 = 3.39168e-09 loss)
I0406 02:25:12.857239 10805 sgd_solver.cpp:106] Iteration 19500, lr = 1e-05
I0406 02:32:25.683033 10805 solver.cpp:242] Iteration 19625 (0.288795 iter/s, 432.832s/125 iter), loss = 6.54746e-06
I0406 02:32:25.683109 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 02:32:25.683120 10805 solver.cpp:261] Train net output #1: loss_coverage = 5.15355e-10 (* 1 = 5.15355e-10 loss)
I0406 02:32:25.683131 10805 sgd_solver.cpp:106] Iteration 19625, lr = 1e-05
I0406 02:39:37.836916 10805 solver.cpp:242] Iteration 19750 (0.289244 iter/s, 432.16s/125 iter), loss = 6.54272e-06
I0406 02:39:37.836989 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 02:39:37.837000 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.02313e-09 (* 1 = 1.02313e-09 loss)
I0406 02:39:37.837013 10805 sgd_solver.cpp:106] Iteration 19750, lr = 1e-05
I0406 02:46:49.987560 10805 solver.cpp:242] Iteration 19875 (0.289247 iter/s, 432.157s/125 iter), loss = 6.53929e-06
I0406 02:46:49.987634 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 02:46:49.987645 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.06543e-08 (* 1 = 1.06543e-08 loss)
I0406 02:46:49.987658 10805 sgd_solver.cpp:106] Iteration 19875, lr = 1e-06
I0406 02:53:58.539825 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_20000.caffemodel
I0406 02:53:58.641858 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_20000.solverstate
I0406 02:53:58.717064 10805 solver.cpp:362] Iteration 20000, Testing net (#0)
I0406 02:53:58.717087 10805 net.cpp:723] Ignoring source layer train_data
I0406 02:53:58.717092 10805 net.cpp:723] Ignoring source layer train_label
I0406 02:53:58.717095 10805 net.cpp:723] Ignoring source layer train_transform
I0406 02:54:30.999261 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 02:54:30.999372 10805 solver.cpp:429] Test net output #1: loss_coverage = 8.4619e-10 (* 1 = 8.4619e-10 loss)
I0406 02:54:30.999383 10805 solver.cpp:429] Test net output #2: mAP = 0
I0406 02:54:30.999392 10805 solver.cpp:429] Test net output #3: precision = 0
I0406 02:54:30.999399 10805 solver.cpp:429] Test net output #4: recall = 0
I0406 02:54:35.118880 10805 solver.cpp:242] Iteration 20000 (0.268737 iter/s, 465.138s/125 iter), loss = 6.53649e-06
I0406 02:54:35.118942 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 02:54:35.118957 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.31995e-10 (* 1 = 4.31995e-10 loss)
I0406 02:54:35.118974 10805 sgd_solver.cpp:106] Iteration 20000, lr = 1e-06
I0406 03:01:50.470944 10805 solver.cpp:242] Iteration 20125 (0.28712 iter/s, 435.359s/125 iter), loss = 6.53434e-06
I0406 03:01:50.471011 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 03:01:50.471021 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.1422e-08 (* 1 = 1.1422e-08 loss)
I0406 03:01:50.471034 10805 sgd_solver.cpp:106] Iteration 20125, lr = 1e-06
I0406 03:09:03.303676 10805 solver.cpp:242] Iteration 20250 (0.288791 iter/s, 432.839s/125 iter), loss = 6.53143e-06
I0406 03:09:03.303800 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 03:09:03.303812 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.36596e-08 (* 1 = 1.36596e-08 loss)
I0406 03:09:03.303824 10805 sgd_solver.cpp:106] Iteration 20250, lr = 1e-06
I0406 03:16:15.755741 10805 solver.cpp:242] Iteration 20375 (0.289045 iter/s, 432.458s/125 iter), loss = 6.53501e-06
I0406 03:16:15.755821 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 03:16:15.755831 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.78319e-09 (* 1 = 1.78319e-09 loss)
I0406 03:16:15.755844 10805 sgd_solver.cpp:106] Iteration 20375, lr = 1e-06
I0406 03:23:27.616432 10805 solver.cpp:242] Iteration 20500 (0.289441 iter/s, 431.867s/125 iter), loss = 6.53057e-06
I0406 03:23:27.616550 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 03:23:27.616561 10805 solver.cpp:261] Train net output #1: loss_coverage = 7.4977e-11 (* 1 = 7.4977e-11 loss)
I0406 03:23:27.616575 10805 sgd_solver.cpp:106] Iteration 20500, lr = 1e-06
I0406 03:30:39.847579 10805 solver.cpp:242] Iteration 20625 (0.289193 iter/s, 432.237s/125 iter), loss = 6.53219e-06
I0406 03:30:39.847703 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 03:30:39.847714 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.36567e-09 (* 1 = 4.36567e-09 loss)
I0406 03:30:39.847728 10805 sgd_solver.cpp:106] Iteration 20625, lr = 1e-06
I0406 03:37:54.548422 10805 solver.cpp:242] Iteration 20750 (0.28755 iter/s, 434.707s/125 iter), loss = 6.53391e-06
I0406 03:37:54.548569 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 03:37:54.548580 10805 solver.cpp:261] Train net output #1: loss_coverage = 9.38454e-10 (* 1 = 9.38454e-10 loss)
I0406 03:37:54.548594 10805 sgd_solver.cpp:106] Iteration 20750, lr = 1e-06
I0406 03:45:09.252274 10805 solver.cpp:242] Iteration 20875 (0.287548 iter/s, 434.71s/125 iter), loss = 6.53462e-06
I0406 03:45:09.252393 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 03:45:09.252403 10805 solver.cpp:261] Train net output #1: loss_coverage = 9.84761e-09 (* 1 = 9.84761e-09 loss)
I0406 03:45:09.252418 10805 sgd_solver.cpp:106] Iteration 20875, lr = 1e-06
I0406 03:52:20.612519 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_21000.caffemodel
I0406 03:52:20.710711 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_21000.solverstate
I0406 03:52:20.785699 10805 solver.cpp:362] Iteration 21000, Testing net (#0)
I0406 03:52:20.785725 10805 net.cpp:723] Ignoring source layer train_data
I0406 03:52:20.785730 10805 net.cpp:723] Ignoring source layer train_label
I0406 03:52:20.785733 10805 net.cpp:723] Ignoring source layer train_transform
I0406 03:52:52.858734 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 03:52:52.858791 10805 solver.cpp:429] Test net output #1: loss_coverage = 8.34755e-10 (* 1 = 8.34755e-10 loss)
I0406 03:52:52.858798 10805 solver.cpp:429] Test net output #2: mAP = 0
I0406 03:52:52.858803 10805 solver.cpp:429] Test net output #3: precision = 0
I0406 03:52:52.858808 10805 solver.cpp:429] Test net output #4: recall = 0
I0406 03:52:56.348748 10805 solver.cpp:242] Iteration 21000 (0.267607 iter/s, 467.103s/125 iter), loss = 6.53097e-06
I0406 03:52:56.348795 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 03:52:56.348805 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.98023e-09 (* 1 = 3.98023e-09 loss)
I0406 03:52:56.348819 10805 sgd_solver.cpp:106] Iteration 21000, lr = 1e-06
I0406 04:00:11.124249 10805 solver.cpp:242] Iteration 21125 (0.2875 iter/s, 434.782s/125 iter), loss = 6.53048e-06
I0406 04:00:11.124322 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 04:00:11.124332 10805 solver.cpp:261] Train net output #1: loss_coverage = 5.41906e-11 (* 1 = 5.41906e-11 loss)
I0406 04:00:11.124346 10805 sgd_solver.cpp:106] Iteration 21125, lr = 1e-06
I0406 04:07:24.149636 10805 solver.cpp:242] Iteration 21250 (0.288662 iter/s, 433.032s/125 iter), loss = 6.53097e-06
I0406 04:07:24.149714 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 04:07:24.149725 10805 solver.cpp:261] Train net output #1: loss_coverage = 5.44506e-09 (* 1 = 5.44506e-09 loss)
I0406 04:07:24.149737 10805 sgd_solver.cpp:106] Iteration 21250, lr = 1e-06
I0406 04:14:39.203225 10805 solver.cpp:242] Iteration 21375 (0.287317 iter/s, 435.06s/125 iter), loss = 6.5302e-06
I0406 04:14:39.203315 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 04:14:39.203325 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.47502e-09 (* 1 = 3.47502e-09 loss)
I0406 04:14:39.203339 10805 sgd_solver.cpp:106] Iteration 21375, lr = 1e-06
I0406 04:21:52.691316 10805 solver.cpp:242] Iteration 21500 (0.288354 iter/s, 433.495s/125 iter), loss = 6.55542e-06
I0406 04:21:52.691385 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 04:21:52.691395 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.49005e-07 (* 1 = 1.49005e-07 loss)
I0406 04:21:52.691408 10805 sgd_solver.cpp:106] Iteration 21500, lr = 1e-06
I0406 04:29:05.204083 10805 solver.cpp:242] Iteration 21625 (0.289004 iter/s, 432.519s/125 iter), loss = 6.53259e-06
I0406 04:29:05.204159 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 04:29:05.204170 10805 solver.cpp:261] Train net output #1: loss_coverage = 5.47872e-10 (* 1 = 5.47872e-10 loss)
I0406 04:29:05.204185 10805 sgd_solver.cpp:106] Iteration 21625, lr = 1e-06
I0406 04:36:17.252943 10805 solver.cpp:242] Iteration 21750 (0.289315 iter/s, 432.055s/125 iter), loss = 6.55189e-06
I0406 04:36:17.253021 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 04:36:17.253031 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.46613e-09 (* 1 = 3.46613e-09 loss)
I0406 04:36:17.253044 10805 sgd_solver.cpp:106] Iteration 21750, lr = 1e-06
I0406 04:43:30.130386 10805 solver.cpp:242] Iteration 21875 (0.288761 iter/s, 432.884s/125 iter), loss = 6.53298e-06
I0406 04:43:30.130553 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 04:43:30.130565 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.14787e-09 (* 1 = 1.14787e-09 loss)
I0406 04:43:30.130578 10805 sgd_solver.cpp:106] Iteration 21875, lr = 1e-06
I0406 04:50:38.737536 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_22000.caffemodel
I0406 04:50:38.833674 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_22000.solverstate
I0406 04:50:38.908130 10805 solver.cpp:362] Iteration 22000, Testing net (#0)
I0406 04:50:38.908155 10805 net.cpp:723] Ignoring source layer train_data
I0406 04:50:38.908160 10805 net.cpp:723] Ignoring source layer train_label
I0406 04:50:38.908164 10805 net.cpp:723] Ignoring source layer train_transform
I0406 04:51:10.887997 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 04:51:10.888092 10805 solver.cpp:429] Test net output #1: loss_coverage = 8.38931e-10 (* 1 = 8.38931e-10 loss)
I0406 04:51:10.888098 10805 solver.cpp:429] Test net output #2: mAP = 0
I0406 04:51:10.888103 10805 solver.cpp:429] Test net output #3: precision = 0
I0406 04:51:10.888108 10805 solver.cpp:429] Test net output #4: recall = 0
I0406 04:51:14.357661 10805 solver.cpp:242] Iteration 22000 (0.269261 iter/s, 464.234s/125 iter), loss = 6.5347e-06
I0406 04:51:14.357702 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 04:51:14.357712 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.19372e-09 (* 1 = 1.19372e-09 loss)
I0406 04:51:14.357723 10805 sgd_solver.cpp:106] Iteration 22000, lr = 1e-06
I0406 04:58:26.599298 10805 solver.cpp:242] Iteration 22125 (0.289186 iter/s, 432.248s/125 iter), loss = 6.53176e-06
I0406 04:58:26.599376 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 04:58:26.599387 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.41359e-09 (* 1 = 2.41359e-09 loss)
I0406 04:58:26.599400 10805 sgd_solver.cpp:106] Iteration 22125, lr = 1e-06
I0406 05:05:39.303400 10805 solver.cpp:242] Iteration 22250 (0.288877 iter/s, 432.711s/125 iter), loss = 6.53014e-06
I0406 05:05:39.303478 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 05:05:39.303488 10805 solver.cpp:261] Train net output #1: loss_coverage = 6.25101e-09 (* 1 = 6.25101e-09 loss)
I0406 05:05:39.303503 10805 sgd_solver.cpp:106] Iteration 22250, lr = 1e-06
I0406 05:12:52.498278 10805 solver.cpp:242] Iteration 22375 (0.288549 iter/s, 433.202s/125 iter), loss = 6.53048e-06
I0406 05:12:52.498353 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 05:12:52.498363 10805 solver.cpp:261] Train net output #1: loss_coverage = 5.18021e-09 (* 1 = 5.18021e-09 loss)
I0406 05:12:52.498375 10805 sgd_solver.cpp:106] Iteration 22375, lr = 1e-06
I0406 05:20:05.133344 10805 solver.cpp:242] Iteration 22500 (0.288923 iter/s, 432.642s/125 iter), loss = 6.53134e-06
I0406 05:20:05.133415 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 05:20:05.133425 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.69778e-09 (* 1 = 4.69778e-09 loss)
I0406 05:20:05.133437 10805 sgd_solver.cpp:106] Iteration 22500, lr = 1e-06
I0406 05:27:17.268983 10805 solver.cpp:242] Iteration 22625 (0.289257 iter/s, 432.142s/125 iter), loss = 6.53217e-06
I0406 05:27:17.269110 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 05:27:17.269121 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.47683e-10 (* 1 = 4.47683e-10 loss)
I0406 05:27:17.269134 10805 sgd_solver.cpp:106] Iteration 22625, lr = 1e-06
I0406 05:34:30.831019 10805 solver.cpp:242] Iteration 22750 (0.288305 iter/s, 433.569s/125 iter), loss = 6.53134e-06
I0406 05:34:30.831135 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 05:34:30.831146 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.45498e-10 (* 1 = 4.45498e-10 loss)
I0406 05:34:30.831159 10805 sgd_solver.cpp:106] Iteration 22750, lr = 1e-06
I0406 05:41:44.518947 10805 solver.cpp:242] Iteration 22875 (0.288221 iter/s, 433.694s/125 iter), loss = 6.53039e-06
I0406 05:41:44.519086 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 05:41:44.519098 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.80589e-09 (* 1 = 2.80589e-09 loss)
I0406 05:41:44.519112 10805 sgd_solver.cpp:106] Iteration 22875, lr = 1e-06
I0406 05:48:53.618865 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_23000.caffemodel
I0406 05:48:53.714979 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_23000.solverstate
I0406 05:48:53.789937 10805 solver.cpp:362] Iteration 23000, Testing net (#0)
I0406 05:48:53.789963 10805 net.cpp:723] Ignoring source layer train_data
I0406 05:48:53.789968 10805 net.cpp:723] Ignoring source layer train_label
I0406 05:48:53.789971 10805 net.cpp:723] Ignoring source layer train_transform
I0406 05:49:25.401727 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 05:49:25.401782 10805 solver.cpp:429] Test net output #1: loss_coverage = 7.80627e-10 (* 1 = 7.80627e-10 loss)
I0406 05:49:25.401787 10805 solver.cpp:429] Test net output #2: mAP = 0
I0406 05:49:25.401792 10805 solver.cpp:429] Test net output #3: precision = 0
I0406 05:49:25.401796 10805 solver.cpp:429] Test net output #4: recall = 0
I0406 05:49:28.864486 10805 solver.cpp:242] Iteration 23000 (0.269192 iter/s, 464.353s/125 iter), loss = 6.53677e-06
I0406 05:49:28.864532 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 05:49:28.864542 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.02524e-08 (* 1 = 1.02524e-08 loss)
I0406 05:49:28.864553 10805 sgd_solver.cpp:106] Iteration 23000, lr = 1e-06
I0406 05:56:44.448463 10805 solver.cpp:242] Iteration 23125 (0.286967 iter/s, 435.591s/125 iter), loss = 6.53255e-06
I0406 05:56:44.448537 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 05:56:44.448549 10805 solver.cpp:261] Train net output #1: loss_coverage = 9.1416e-09 (* 1 = 9.1416e-09 loss)
I0406 05:56:44.448560 10805 sgd_solver.cpp:106] Iteration 23125, lr = 1e-06
I0406 06:03:57.373148 10805 solver.cpp:242] Iteration 23250 (0.288729 iter/s, 432.931s/125 iter), loss = 6.53045e-06
I0406 06:03:57.373224 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 06:03:57.373234 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.98982e-10 (* 1 = 2.98982e-10 loss)
I0406 06:03:57.373247 10805 sgd_solver.cpp:106] Iteration 23250, lr = 1e-06
I0406 06:11:11.012609 10805 solver.cpp:242] Iteration 23375 (0.288254 iter/s, 433.646s/125 iter), loss = 6.53053e-06
I0406 06:11:11.012686 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 06:11:11.012696 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.9253e-09 (* 1 = 1.9253e-09 loss)
I0406 06:11:11.012707 10805 sgd_solver.cpp:106] Iteration 23375, lr = 1e-06
I0406 06:18:24.116204 10805 solver.cpp:242] Iteration 23500 (0.28861 iter/s, 433.11s/125 iter), loss = 6.53117e-06
I0406 06:18:24.116336 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 06:18:24.116348 10805 solver.cpp:261] Train net output #1: loss_coverage = 7.8456e-10 (* 1 = 7.8456e-10 loss)
I0406 06:18:24.116361 10805 sgd_solver.cpp:106] Iteration 23500, lr = 1e-06
I0406 06:25:36.893784 10805 solver.cpp:242] Iteration 23625 (0.288828 iter/s, 432.784s/125 iter), loss = 6.53676e-06
I0406 06:25:36.893864 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 06:25:36.893874 10805 solver.cpp:261] Train net output #1: loss_coverage = 5.77392e-09 (* 1 = 5.77392e-09 loss)
I0406 06:25:36.893888 10805 sgd_solver.cpp:106] Iteration 23625, lr = 1e-06
I0406 06:32:49.253996 10805 solver.cpp:242] Iteration 23750 (0.289106 iter/s, 432.367s/125 iter), loss = 6.53068e-06
I0406 06:32:49.254159 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 06:32:49.254171 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.21361e-09 (* 1 = 1.21361e-09 loss)
I0406 06:32:49.254185 10805 sgd_solver.cpp:106] Iteration 23750, lr = 1e-06
I0406 06:40:01.409497 10805 solver.cpp:242] Iteration 23875 (0.289243 iter/s, 432.162s/125 iter), loss = 6.53032e-06
I0406 06:40:01.409628 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 06:40:01.409641 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.12226e-09 (* 1 = 1.12226e-09 loss)
I0406 06:40:01.409653 10805 sgd_solver.cpp:106] Iteration 23875, lr = 1e-06
I0406 06:47:11.437134 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_24000.caffemodel
I0406 06:47:11.534204 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_24000.solverstate
I0406 06:47:11.609367 10805 solver.cpp:362] Iteration 24000, Testing net (#0)
I0406 06:47:11.609391 10805 net.cpp:723] Ignoring source layer train_data
I0406 06:47:11.609396 10805 net.cpp:723] Ignoring source layer train_label
I0406 06:47:11.609400 10805 net.cpp:723] Ignoring source layer train_transform
I0406 06:47:43.077966 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 06:47:43.078075 10805 solver.cpp:429] Test net output #1: loss_coverage = 7.31159e-10 (* 1 = 7.31159e-10 loss)
I0406 06:47:43.078083 10805 solver.cpp:429] Test net output #2: mAP = 0
I0406 06:47:43.078088 10805 solver.cpp:429] Test net output #3: precision = 0
I0406 06:47:43.078092 10805 solver.cpp:429] Test net output #4: recall = 0
I0406 06:47:46.563063 10805 solver.cpp:242] Iteration 24000 (0.268724 iter/s, 465.161s/125 iter), loss = 6.53208e-06
I0406 06:47:46.563107 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 06:47:46.563117 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.38015e-08 (* 1 = 1.38015e-08 loss)
I0406 06:47:46.563128 10805 sgd_solver.cpp:106] Iteration 24000, lr = 1e-06
I0406 06:54:58.268396 10805 solver.cpp:242] Iteration 24125 (0.289545 iter/s, 431.712s/125 iter), loss = 6.54499e-06
I0406 06:54:58.268525 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 06:54:58.268537 10805 solver.cpp:261] Train net output #1: loss_coverage = 6.62372e-10 (* 1 = 6.62372e-10 loss)
I0406 06:54:58.268549 10805 sgd_solver.cpp:106] Iteration 24125, lr = 1e-06
I0406 07:02:12.571012 10805 solver.cpp:242] Iteration 24250 (0.287814 iter/s, 434.309s/125 iter), loss = 6.53041e-06
I0406 07:02:12.571117 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 07:02:12.571128 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.18376e-09 (* 1 = 1.18376e-09 loss)
I0406 07:02:12.571141 10805 sgd_solver.cpp:106] Iteration 24250, lr = 1e-06
I0406 07:09:24.147227 10805 solver.cpp:242] Iteration 24375 (0.289632 iter/s, 431.583s/125 iter), loss = 6.53267e-06
I0406 07:09:24.147352 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 07:09:24.147362 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.2637e-09 (* 1 = 3.2637e-09 loss)
I0406 07:09:24.147375 10805 sgd_solver.cpp:106] Iteration 24375, lr = 1e-06
I0406 07:16:35.518563 10805 solver.cpp:242] Iteration 24500 (0.289769 iter/s, 431.378s/125 iter), loss = 6.53386e-06
I0406 07:16:35.518630 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 07:16:35.518640 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.73722e-09 (* 1 = 1.73722e-09 loss)
I0406 07:16:35.518652 10805 sgd_solver.cpp:106] Iteration 24500, lr = 1e-06
I0406 07:23:44.624125 10805 solver.cpp:242] Iteration 24625 (0.2913 iter/s, 429.112s/125 iter), loss = 6.53532e-06
I0406 07:23:44.624297 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 07:23:44.624310 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.16247e-09 (* 1 = 3.16247e-09 loss)
I0406 07:23:44.624323 10805 sgd_solver.cpp:106] Iteration 24625, lr = 1e-06
I0406 07:30:53.953608 10805 solver.cpp:242] Iteration 24750 (0.291148 iter/s, 429.335s/125 iter), loss = 6.53075e-06
I0406 07:30:53.953753 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 07:30:53.953765 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.18262e-09 (* 1 = 2.18262e-09 loss)
I0406 07:30:53.953779 10805 sgd_solver.cpp:106] Iteration 24750, lr = 1e-06
I0406 07:38:06.523840 10805 solver.cpp:242] Iteration 24875 (0.288966 iter/s, 432.577s/125 iter), loss = 6.53225e-06
I0406 07:38:06.523963 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 07:38:06.523974 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.1048e-09 (* 1 = 3.1048e-09 loss)
I0406 07:38:06.523986 10805 sgd_solver.cpp:106] Iteration 24875, lr = 1e-06
I0406 07:45:15.640419 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_25000.caffemodel
I0406 07:45:15.736692 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_25000.solverstate
I0406 07:45:15.811134 10805 solver.cpp:362] Iteration 25000, Testing net (#0)
I0406 07:45:15.811159 10805 net.cpp:723] Ignoring source layer train_data
I0406 07:45:15.811163 10805 net.cpp:723] Ignoring source layer train_label
I0406 07:45:15.811167 10805 net.cpp:723] Ignoring source layer train_transform
I0406 07:45:47.825623 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 07:45:47.825677 10805 solver.cpp:429] Test net output #1: loss_coverage = 7.31892e-10 (* 1 = 7.31892e-10 loss)
I0406 07:45:47.825685 10805 solver.cpp:429] Test net output #2: mAP = 0
I0406 07:45:47.825688 10805 solver.cpp:429] Test net output #3: precision = 0
I0406 07:45:47.825693 10805 solver.cpp:429] Test net output #4: recall = 0
I0406 07:45:51.253937 10805 solver.cpp:242] Iteration 25000 (0.268969 iter/s, 464.737s/125 iter), loss = 6.53479e-06
I0406 07:45:51.253983 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 07:45:51.253993 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.07301e-09 (* 1 = 1.07301e-09 loss)
I0406 07:45:51.254005 10805 sgd_solver.cpp:106] Iteration 25000, lr = 1e-06
I0406 07:53:03.163422 10805 solver.cpp:242] Iteration 25125 (0.289408 iter/s, 431.916s/125 iter), loss = 6.53213e-06
I0406 07:53:03.163519 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 07:53:03.163538 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.21616e-08 (* 1 = 1.21616e-08 loss)
I0406 07:53:03.163556 10805 sgd_solver.cpp:106] Iteration 25125, lr = 1e-06
I0406 08:00:13.311348 10805 solver.cpp:242] Iteration 25250 (0.290593 iter/s, 430.154s/125 iter), loss = 6.53638e-06
I0406 08:00:13.311424 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 08:00:13.311434 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.41866e-09 (* 1 = 3.41866e-09 loss)
I0406 08:00:13.311447 10805 sgd_solver.cpp:106] Iteration 25250, lr = 1e-06
I0406 08:07:24.076512 10805 solver.cpp:242] Iteration 25375 (0.290177 iter/s, 430.772s/125 iter), loss = 6.53215e-06
I0406 08:07:24.076643 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 08:07:24.076655 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.27762e-10 (* 1 = 3.27762e-10 loss)
I0406 08:07:24.076668 10805 sgd_solver.cpp:106] Iteration 25375, lr = 1e-06
I0406 08:14:34.278614 10805 solver.cpp:242] Iteration 25500 (0.290557 iter/s, 430.208s/125 iter), loss = 6.53111e-06
I0406 08:14:34.278704 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 08:14:34.278715 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.29444e-09 (* 1 = 1.29444e-09 loss)
I0406 08:14:34.278728 10805 sgd_solver.cpp:106] Iteration 25500, lr = 1e-06
I0406 08:21:43.823477 10805 solver.cpp:242] Iteration 25625 (0.291001 iter/s, 429.551s/125 iter), loss = 6.5358e-06
I0406 08:21:43.823640 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 08:21:43.823652 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.70504e-09 (* 1 = 1.70504e-09 loss)
I0406 08:21:43.823667 10805 sgd_solver.cpp:106] Iteration 25625, lr = 1e-06
I0406 08:28:55.175989 10805 solver.cpp:242] Iteration 25750 (0.289782 iter/s, 431.359s/125 iter), loss = 6.52934e-06
I0406 08:28:55.176126 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 08:28:55.176137 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.61877e-10 (* 1 = 1.61877e-10 loss)
I0406 08:28:55.176151 10805 sgd_solver.cpp:106] Iteration 25750, lr = 1e-06
I0406 08:36:05.707108 10805 solver.cpp:242] Iteration 25875 (0.290335 iter/s, 430.537s/125 iter), loss = 6.53325e-06
I0406 08:36:05.707178 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 08:36:05.707188 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.09e-09 (* 1 = 1.09e-09 loss)
I0406 08:36:05.707201 10805 sgd_solver.cpp:106] Iteration 25875, lr = 1e-06
I0406 08:43:13.369704 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_26000.caffemodel
I0406 08:43:13.465740 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_26000.solverstate
I0406 08:43:13.540302 10805 solver.cpp:362] Iteration 26000, Testing net (#0)
I0406 08:43:13.540326 10805 net.cpp:723] Ignoring source layer train_data
I0406 08:43:13.540330 10805 net.cpp:723] Ignoring source layer train_label
I0406 08:43:13.540334 10805 net.cpp:723] Ignoring source layer train_transform
I0406 08:43:45.891346 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 08:43:45.891400 10805 solver.cpp:429] Test net output #1: loss_coverage = 6.95358e-10 (* 1 = 6.95358e-10 loss)
I0406 08:43:45.891407 10805 solver.cpp:429] Test net output #2: mAP = 0
I0406 08:43:45.891412 10805 solver.cpp:429] Test net output #3: precision = 0
I0406 08:43:45.891415 10805 solver.cpp:429] Test net output #4: recall = 0
I0406 08:43:49.300483 10805 solver.cpp:242] Iteration 26000 (0.269629 iter/s, 463.6s/125 iter), loss = 6.53207e-06
I0406 08:43:49.300530 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 08:43:49.300540 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.47446e-09 (* 1 = 3.47446e-09 loss)
I0406 08:43:49.300552 10805 sgd_solver.cpp:106] Iteration 26000, lr = 1e-06
I0406 08:50:59.935448 10805 solver.cpp:242] Iteration 26125 (0.290265 iter/s, 430.641s/125 iter), loss = 6.53256e-06
I0406 08:50:59.935523 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 08:50:59.935533 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.02335e-08 (* 1 = 1.02335e-08 loss)
I0406 08:50:59.935544 10805 sgd_solver.cpp:106] Iteration 26125, lr = 1e-06
I0406 08:58:09.955624 10805 solver.cpp:242] Iteration 26250 (0.29068 iter/s, 430.026s/125 iter), loss = 6.53718e-06
I0406 08:58:09.955750 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 08:58:09.955761 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.17548e-09 (* 1 = 1.17548e-09 loss)
I0406 08:58:09.955775 10805 sgd_solver.cpp:106] Iteration 26250, lr = 1e-06
I0406 09:05:20.449163 10805 solver.cpp:242] Iteration 26375 (0.29036 iter/s, 430.5s/125 iter), loss = 6.52968e-06
I0406 09:05:20.449230 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 09:05:20.449242 10805 solver.cpp:261] Train net output #1: loss_coverage = 5.41513e-10 (* 1 = 5.41513e-10 loss)
I0406 09:05:20.449254 10805 sgd_solver.cpp:106] Iteration 26375, lr = 1e-06
I0406 09:12:31.474359 10805 solver.cpp:242] Iteration 26500 (0.290002 iter/s, 431.031s/125 iter), loss = 6.53061e-06
I0406 09:12:31.474465 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 09:12:31.474478 10805 solver.cpp:261] Train net output #1: loss_coverage = 9.67537e-10 (* 1 = 9.67537e-10 loss)
I0406 09:12:31.474491 10805 sgd_solver.cpp:106] Iteration 26500, lr = 1e-06
I0406 09:19:42.124521 10805 solver.cpp:242] Iteration 26625 (0.290255 iter/s, 430.656s/125 iter), loss = 6.5326e-06
I0406 09:19:42.124660 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 09:19:42.124670 10805 solver.cpp:261] Train net output #1: loss_coverage = 5.63709e-10 (* 1 = 5.63709e-10 loss)
I0406 09:19:42.124683 10805 sgd_solver.cpp:106] Iteration 26625, lr = 1e-06
I0406 09:26:55.107861 10805 solver.cpp:242] Iteration 26750 (0.28869 iter/s, 432.99s/125 iter), loss = 6.53086e-06
I0406 09:26:55.107938 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 09:26:55.107949 10805 solver.cpp:261] Train net output #1: loss_coverage = 6.76885e-09 (* 1 = 6.76885e-09 loss)
I0406 09:26:55.107961 10805 sgd_solver.cpp:106] Iteration 26750, lr = 1e-06
I0406 09:34:03.274569 10805 solver.cpp:242] Iteration 26875 (0.291939 iter/s, 428.172s/125 iter), loss = 6.52917e-06
I0406 09:34:03.274684 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 09:34:03.274713 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.43e-09 (* 1 = 1.43e-09 loss)
I0406 09:34:03.274727 10805 sgd_solver.cpp:106] Iteration 26875, lr = 1e-06
I0406 09:41:14.650442 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_27000.caffemodel
I0406 09:41:14.746868 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_27000.solverstate
I0406 09:41:14.821430 10805 solver.cpp:362] Iteration 27000, Testing net (#0)
I0406 09:41:14.821455 10805 net.cpp:723] Ignoring source layer train_data
I0406 09:41:14.821460 10805 net.cpp:723] Ignoring source layer train_label
I0406 09:41:14.821462 10805 net.cpp:723] Ignoring source layer train_transform
I0406 09:41:46.293298 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 09:41:46.293352 10805 solver.cpp:429] Test net output #1: loss_coverage = 6.81462e-10 (* 1 = 6.81462e-10 loss)
I0406 09:41:46.293359 10805 solver.cpp:429] Test net output #2: mAP = 0
I0406 09:41:46.293365 10805 solver.cpp:429] Test net output #3: precision = 0
I0406 09:41:46.293368 10805 solver.cpp:429] Test net output #4: recall = 0
I0406 09:41:49.807250 10805 solver.cpp:242] Iteration 27000 (0.26793 iter/s, 466.539s/125 iter), loss = 6.53273e-06
I0406 09:41:49.807297 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 09:41:49.807307 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.84014e-08 (* 1 = 1.84014e-08 loss)
I0406 09:41:49.807319 10805 sgd_solver.cpp:106] Iteration 27000, lr = 1e-06
I0406 09:49:04.339931 10805 solver.cpp:242] Iteration 27125 (0.287661 iter/s, 434.54s/125 iter), loss = 6.53772e-06
I0406 09:49:04.340070 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 09:49:04.340080 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.56711e-08 (* 1 = 3.56711e-08 loss)
I0406 09:49:04.340095 10805 sgd_solver.cpp:106] Iteration 27125, lr = 1e-06
I0406 09:56:18.198752 10805 solver.cpp:242] Iteration 27250 (0.288108 iter/s, 433.866s/125 iter), loss = 6.52996e-06
I0406 09:56:18.198853 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 09:56:18.198864 10805 solver.cpp:261] Train net output #1: loss_coverage = 6.78008e-11 (* 1 = 6.78008e-11 loss)
I0406 09:56:18.198878 10805 sgd_solver.cpp:106] Iteration 27250, lr = 1e-06
I0406 10:03:32.548254 10805 solver.cpp:242] Iteration 27375 (0.287782 iter/s, 434.356s/125 iter), loss = 6.53131e-06
I0406 10:03:32.548328 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 10:03:32.548339 10805 solver.cpp:261] Train net output #1: loss_coverage = 6.18646e-10 (* 1 = 6.18646e-10 loss)
I0406 10:03:32.548352 10805 sgd_solver.cpp:106] Iteration 27375, lr = 1e-06
I0406 10:10:46.676048 10805 solver.cpp:242] Iteration 27500 (0.287929 iter/s, 434.135s/125 iter), loss = 6.5359e-06
I0406 10:10:46.676141 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 10:10:46.676151 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.70488e-10 (* 1 = 3.70488e-10 loss)
I0406 10:10:46.676162 10805 sgd_solver.cpp:106] Iteration 27500, lr = 1e-06
I0406 10:18:00.522123 10805 solver.cpp:242] Iteration 27625 (0.288116 iter/s, 433.853s/125 iter), loss = 6.5316e-06
I0406 10:18:00.522261 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 10:18:00.522274 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.55168e-10 (* 1 = 3.55168e-10 loss)
I0406 10:18:00.522286 10805 sgd_solver.cpp:106] Iteration 27625, lr = 1e-06
I0406 10:25:14.787474 10805 solver.cpp:242] Iteration 27750 (0.287838 iter/s, 434.272s/125 iter), loss = 6.52998e-06
I0406 10:25:14.787542 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 10:25:14.787552 10805 solver.cpp:261] Train net output #1: loss_coverage = 5.18496e-10 (* 1 = 5.18496e-10 loss)
I0406 10:25:14.787564 10805 sgd_solver.cpp:106] Iteration 27750, lr = 1e-06
I0406 10:32:29.389204 10805 solver.cpp:242] Iteration 27875 (0.287615 iter/s, 434.609s/125 iter), loss = 6.52934e-06
I0406 10:32:29.389281 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 10:32:29.389292 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.00346e-09 (* 1 = 1.00346e-09 loss)
I0406 10:32:29.389309 10805 sgd_solver.cpp:106] Iteration 27875, lr = 1e-06
I0406 10:39:39.822311 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_28000.caffemodel
I0406 10:39:39.924336 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_28000.solverstate
I0406 10:39:40.003937 10805 solver.cpp:362] Iteration 28000, Testing net (#0)
I0406 10:39:40.003962 10805 net.cpp:723] Ignoring source layer train_data
I0406 10:39:40.003968 10805 net.cpp:723] Ignoring source layer train_label
I0406 10:39:40.003970 10805 net.cpp:723] Ignoring source layer train_transform
I0406 10:40:11.822125 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 10:40:11.822228 10805 solver.cpp:429] Test net output #1: loss_coverage = 6.91513e-10 (* 1 = 6.91513e-10 loss)
I0406 10:40:11.822237 10805 solver.cpp:429] Test net output #2: mAP = 0
I0406 10:40:11.822240 10805 solver.cpp:429] Test net output #3: precision = 0
I0406 10:40:11.822245 10805 solver.cpp:429] Test net output #4: recall = 0
I0406 10:40:15.280676 10805 solver.cpp:242] Iteration 28000 (0.268298 iter/s, 465.899s/125 iter), loss = 6.53393e-06
I0406 10:40:15.280724 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 10:40:15.280733 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.54849e-10 (* 1 = 4.54849e-10 loss)
I0406 10:40:15.280746 10805 sgd_solver.cpp:106] Iteration 28000, lr = 1e-06
I0406 10:47:29.700605 10805 solver.cpp:242] Iteration 28125 (0.287735 iter/s, 434.427s/125 iter), loss = 6.53154e-06
I0406 10:47:29.700731 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 10:47:29.700743 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.53715e-10 (* 1 = 3.53715e-10 loss)
I0406 10:47:29.700757 10805 sgd_solver.cpp:106] Iteration 28125, lr = 1e-06
I0406 10:54:44.088933 10805 solver.cpp:242] Iteration 28250 (0.287756 iter/s, 434.395s/125 iter), loss = 6.5372e-06
I0406 10:54:44.089063 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 10:54:44.089074 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.71455e-09 (* 1 = 1.71455e-09 loss)
I0406 10:54:44.089087 10805 sgd_solver.cpp:106] Iteration 28250, lr = 1e-06
I0406 11:01:58.601354 10805 solver.cpp:242] Iteration 28375 (0.287674 iter/s, 434.519s/125 iter), loss = 6.53395e-06
I0406 11:01:58.601487 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 11:01:58.601498 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.84501e-08 (* 1 = 1.84501e-08 loss)
I0406 11:01:58.601511 10805 sgd_solver.cpp:106] Iteration 28375, lr = 1e-06
I0406 11:09:13.153523 10805 solver.cpp:242] Iteration 28500 (0.287648 iter/s, 434.559s/125 iter), loss = 6.53071e-06
I0406 11:09:13.153600 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 11:09:13.153610 10805 solver.cpp:261] Train net output #1: loss_coverage = 3.30734e-10 (* 1 = 3.30734e-10 loss)
I0406 11:09:13.153623 10805 sgd_solver.cpp:106] Iteration 28500, lr = 1e-06
I0406 11:16:27.601052 10805 solver.cpp:242] Iteration 28625 (0.287717 iter/s, 434.455s/125 iter), loss = 6.53395e-06
I0406 11:16:27.601121 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 11:16:27.601130 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.27296e-09 (* 1 = 4.27296e-09 loss)
I0406 11:16:27.601142 10805 sgd_solver.cpp:106] Iteration 28625, lr = 1e-06
I0406 11:23:41.707911 10805 solver.cpp:242] Iteration 28750 (0.287943 iter/s, 434.114s/125 iter), loss = 6.53007e-06
I0406 11:23:41.707979 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 11:23:41.707989 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.48329e-10 (* 1 = 2.48329e-10 loss)
I0406 11:23:41.708001 10805 sgd_solver.cpp:106] Iteration 28750, lr = 1e-06
I0406 11:30:55.653883 10805 solver.cpp:242] Iteration 28875 (0.28805 iter/s, 433.953s/125 iter), loss = 6.53212e-06
I0406 11:30:55.653961 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 11:30:55.653971 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.44147e-09 (* 1 = 1.44147e-09 loss)
I0406 11:30:55.653983 10805 sgd_solver.cpp:106] Iteration 28875, lr = 1e-06
I0406 11:38:00.998003 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_29000.caffemodel
I0406 11:38:01.094853 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_29000.solverstate
I0406 11:38:01.169528 10805 solver.cpp:362] Iteration 29000, Testing net (#0)
I0406 11:38:01.169554 10805 net.cpp:723] Ignoring source layer train_data
I0406 11:38:01.169559 10805 net.cpp:723] Ignoring source layer train_label
I0406 11:38:01.169564 10805 net.cpp:723] Ignoring source layer train_transform
I0406 11:38:32.217739 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 11:38:32.217790 10805 solver.cpp:429] Test net output #1: loss_coverage = 7.29154e-10 (* 1 = 7.29154e-10 loss)
I0406 11:38:32.217797 10805 solver.cpp:429] Test net output #2: mAP = 0
I0406 11:38:32.217802 10805 solver.cpp:429] Test net output #3: precision = 0
I0406 11:38:32.217806 10805 solver.cpp:429] Test net output #4: recall = 0
I0406 11:38:35.631494 10805 solver.cpp:242] Iteration 29000 (0.271749 iter/s, 459.984s/125 iter), loss = 6.53065e-06
I0406 11:38:35.631539 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 11:38:35.631548 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.07701e-09 (* 1 = 2.07701e-09 loss)
I0406 11:38:35.631561 10805 sgd_solver.cpp:106] Iteration 29000, lr = 1e-06
I0406 11:45:42.940804 10805 solver.cpp:242] Iteration 29125 (0.292524 iter/s, 427.315s/125 iter), loss = 6.54308e-06
I0406 11:45:42.940878 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 11:45:42.940888 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.76629e-10 (* 1 = 1.76629e-10 loss)
I0406 11:45:42.940901 10805 sgd_solver.cpp:106] Iteration 29125, lr = 1e-06
I0406 11:52:56.831182 10805 solver.cpp:242] Iteration 29250 (0.288087 iter/s, 433.897s/125 iter), loss = 6.53051e-06
I0406 11:52:56.831264 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 11:52:56.831274 10805 solver.cpp:261] Train net output #1: loss_coverage = 4.42687e-10 (* 1 = 4.42687e-10 loss)
I0406 11:52:56.831287 10805 sgd_solver.cpp:106] Iteration 29250, lr = 1e-06
I0406 12:00:07.724827 10805 solver.cpp:242] Iteration 29375 (0.290091 iter/s, 430.899s/125 iter), loss = 6.53857e-06
I0406 12:00:07.724947 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 12:00:07.724959 10805 solver.cpp:261] Train net output #1: loss_coverage = 8.47981e-10 (* 1 = 8.47981e-10 loss)
I0406 12:00:07.724973 10805 sgd_solver.cpp:106] Iteration 29375, lr = 1e-06
I0406 12:07:16.337436 10805 solver.cpp:242] Iteration 29500 (0.291635 iter/s, 428.618s/125 iter), loss = 6.53089e-06
I0406 12:07:16.337566 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 12:07:16.337577 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.00294e-08 (* 1 = 1.00294e-08 loss)
I0406 12:07:16.337590 10805 sgd_solver.cpp:106] Iteration 29500, lr = 1e-06
I0406 12:14:24.872573 10805 solver.cpp:242] Iteration 29625 (0.291688 iter/s, 428.54s/125 iter), loss = 6.53035e-06
I0406 12:14:24.872654 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 12:14:24.872664 10805 solver.cpp:261] Train net output #1: loss_coverage = 2.2484e-09 (* 1 = 2.2484e-09 loss)
I0406 12:14:24.872678 10805 sgd_solver.cpp:106] Iteration 29625, lr = 1e-06
I0406 12:21:32.866647 10805 solver.cpp:242] Iteration 29750 (0.292057 iter/s, 427.999s/125 iter), loss = 6.52945e-06
I0406 12:21:32.866732 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 12:21:32.866744 10805 solver.cpp:261] Train net output #1: loss_coverage = 9.7428e-10 (* 1 = 9.7428e-10 loss)
I0406 12:21:32.866756 10805 sgd_solver.cpp:106] Iteration 29750, lr = 1e-07
I0406 12:28:42.800148 10805 solver.cpp:242] Iteration 29875 (0.290739 iter/s, 429.939s/125 iter), loss = 6.53096e-06
I0406 12:28:42.800230 10805 solver.cpp:261] Train net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 12:28:42.800240 10805 solver.cpp:261] Train net output #1: loss_coverage = 1.3959e-09 (* 1 = 1.3959e-09 loss)
I0406 12:28:42.800254 10805 sgd_solver.cpp:106] Iteration 29875, lr = 1e-07
I0406 12:35:48.325865 10805 solver.cpp:479] Snapshotting to binary proto file snapshot_iter_30000.caffemodel
I0406 12:35:48.422133 10805 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_30000.solverstate
I0406 12:35:48.759629 10805 solver.cpp:342] Iteration 30000, loss = 6.53244e-06
I0406 12:35:48.759667 10805 solver.cpp:362] Iteration 30000, Testing net (#0)
I0406 12:35:48.759675 10805 net.cpp:723] Ignoring source layer train_data
I0406 12:35:48.759680 10805 net.cpp:723] Ignoring source layer train_label
I0406 12:35:48.759685 10805 net.cpp:723] Ignoring source layer train_transform
I0406 12:36:21.017391 10805 solver.cpp:429] Test net output #0: loss_bbox = 0 (* 2 = 0 loss)
I0406 12:36:21.017444 10805 solver.cpp:429] Test net output #1: loss_coverage = 7.13915e-10 (* 1 = 7.13915e-10 loss)
I0406 12:36:21.017452 10805 solver.cpp:429] Test net output #2: mAP = 0
I0406 12:36:21.017455 10805 solver.cpp:429] Test net output #3: precision = 0
I0406 12:36:21.017460 10805 solver.cpp:429] Test net output #4: recall = 0
I0406 12:36:21.017464 10805 solver.cpp:347] Optimization Done.
I0406 12:36:21.017468 10805 caffe.cpp:234] Optimization Done.