Error when run PVAnet_test

[autumnqin]

python dv.py --model ~/PVAnet_iter_70000.ckpt --net PVAnet_test

NotFoundError (see above for traceback): Key conv5_4/last_bn_scale/beta not found in checkpoint;

W tensorflow/core/framework/op_kernel.cc:993] Not found: Key conv5_4/last_bn_scale/beta not found in checkpoint
W tensorflow/core/framework/op_kernel.cc:993] Not found: Key conv5_4/last_bn_scale/alpha not found in checkpoint
W tensorflow/core/framework/op_kernel.cc:993] Not found: Key conv5_4/last_bn_scale/beta not found in checkpoint
[[Node: save/RestoreV2_473 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/RestoreV2_473/tensor_names, save/RestoreV2_473/shape_and_slices)]]
W tensorflow/core/framework/op_kernel.cc:993] Not found: Key conv5_4/last_bn_scale/beta not found in checkpoint
[[Node: save/RestoreV2_473 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/RestoreV2_473/tensor_names, save/RestoreV2_473/shape_and_slices)]]
W tensorflow/core/framework/op_kernel.cc:993] Not found: Key conv5_4/last_bn_scale/beta not found in checkpoint
[[Node: save/RestoreV2_473 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/RestoreV2_473/tensor_names, save/RestoreV2_473/shape_and_slices)]]
W tensorflow/core/framework/op_kernel.cc:993] Not found: Key conv5_4/last_bn_scale/beta not found in checkpoint
[[Node: save/RestoreV2_473 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/RestoreV2_473/tensor_names, save/RestoreV2_473/shape_and_slices)]]
W tensorflow/core/framework/op_kernel.cc:993] Not found: Key conv5_4/last_bn_scale/beta not found in checkpoint
[[Node: save/RestoreV2_473 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/RestoreV2_473/tensor_names, save/RestoreV2_473/shape_and_slices)]]
W tensorflow/core/framework/op_kernel.cc:993] Not found: Key conv5_4/last_bn_scale/beta not found in checkpoint
[[Node: save/RestoreV2_473 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/RestoreV2_473/tensor_names, save/RestoreV2_473/shape_and_slices)]]

[CharlesShang]

Was it solved?
There must be a typo in the test net.
I'll run some debug in my spare time

[jwnsu]

test error is easy to resolve, however it has very high error (mAP is below 0.1) -- caffe version is one of most accurate models. It seems conv2_1/1/conv layer is different from the paper, can also be caused by issue in pva_negation_block/v2.

[autumnqin]

train is different from test, and both are different from Caffe version

[baileyqbb]

Hi, there! I faced the same issue, but finally find the errors in PVAnet_test.py. Here is the lines I've changed to make the test work:
lines to comment:
85 --> .scale(c_in=384, name='conv5_4/last_bn_scale')
118 --> (self.feed('convf_rpn', 'convf_2')
119 --> .concat(axis=3, name='convf'))

lines to change:
92 --> (self.feed('downsample', 'conv4_4', 'upsamle') ---> (self.feed('downsample', 'conv4_4')
121 --> (self.feed('convf', 'rois') ---> (self.feed('convf_2', 'rois')
122 --> .roi_pool(7, 7, 1.0/16, name='roi_pooling') ---> .roi_pool(6, 6, 1.0/16, name='roi_pooling')

Hope this will help!

BTW, as mentioned by @jwnsu, test error is quite high. I trained the model using VOC2012 data with 200000 iters, the mAP is about 0.03, which is totally unacceptable. I am gonna train the model with more iters, and meanwhile, check the PVAnet to see if it is the same with the caffe version mentioned by @autumnqin.

Will update if any news.

[sevaxyz]

@baileyqbb Haven't you figured out the issue with the low mAP by any chance?

[yshen92]

Hi guys, can anyone please share some tips on improving the mAP?

[QueenJuliaZxx]

thank you very much @baileyqbb

[gentlebreeze1]

@baileyqbb @QueenJuliaZxx do you run pva-faster-rcnn successfully?my pva.npy seem to be wrong.where do you download?what the script command do you run ?thanks for your help

[amirmgh1375]

@baileyqbb
thank you so much 👍
it works very well 💯 🥇