Issue

[BaldyLLC]

It is not allowing me to render

[errno-mmd]

The screeenshot image is too small to read the error message...

[BaldyLLC]

C:\Users\lewis.conda\envs\mmdmat\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
C:\Users\lewis.conda\envs\mmdmat\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
C:\Users\lewis.conda\envs\mmdmat\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
C:\Users\lewis.conda\envs\mmdmat\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
C:\Users\lewis.conda\envs\mmdmat\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
np_resource = np.dtype([("resource", np.ubyte, 1)])
WARNING:tensorflow:From C:\Users\lewis\Downloads\mmdmatic-ver1.03-3\mmdmatic-ver1.03-3\tf-pose-estimation\tf_pose\mobilenet\mobilenet.py:369: The name tf.nn.avg_pool is deprecated. Please use tf.nn.avg_pool2d instead.

usage: run_video.py [-h] [--video VIDEO] [--resolution RESOLUTION]
[--model MODEL] [--show-process] [--no_bg]
[--write_json WRITE_JSON] [--no_display]
[--resize_out_ratio RESIZE_OUT_RATIO]
[--number_people_max NUMBER_PEOPLE_MAX]
[--frame_first FRAME_FIRST] [--write_video WRITE_VIDEO]
[--tensorrt TENSORRT]
run_video.py: error: unrecognized arguments: 5/1/_215002\zimzalabim_json 5/1/_215002\zimzalabim_tf-pose-estimation.avi

Done!!
tf-pose-estimation analysis end
BULK OUTPUT_JSON_DIR: C:\Users\lewis\Downloads\zimzalabim_Mon 5/1/_215002\zimzalabim_json

mannequinchallenge-vmd

usage: predict_video.py [-h] --input {single_view,two_view,two_view_k}
[--simple_keypoints SIMPLE_KEYPOINTS] [--mode MODE]
[--human_data_term HUMAN_DATA_TERM]
[--batchSize BATCHSIZE] [--loadSize LOADSIZE]
[--fineSize FINESIZE] [--output_nc OUTPUT_NC]
[--ngf NGF] [--ndf NDF]
[--which_model_netG WHICH_MODEL_NETG]
[--gpu_ids GPU_IDS] [--name NAME] [--model MODEL]
[--nThreads NTHREADS]
[--checkpoints_dir CHECKPOINTS_DIR] [--norm NORM]
[--serial_batches] [--display_winsize DISPLAY_WINSIZE]
[--display_id DISPLAY_ID] [--identity IDENTITY]
[--use_dropout] [--max_dataset_size MAX_DATASET_SIZE]
[--display_freq DISPLAY_FREQ]
[--print_freq PRINT_FREQ]
[--save_latest_freq SAVE_LATEST_FREQ]
[--save_epoch_freq SAVE_EPOCH_FREQ] [--continue_train]
[--phase PHASE] [--which_epoch WHICH_EPOCH]
[--niter NITER] [--niter_decay NITER_DECAY]
[--lr_decay_epoch LR_DECAY_EPOCH]
[--lr_policy LR_POLICY] [--beta1 BETA1] [--lr LR]
[--no_lsgan] [--lambda_A LAMBDA_A]
[--lambda_B LAMBDA_B] [--pool_size POOL_SIZE]
[--no_html] [--no_flip] [--video_path VIDEO_PATH]
[--json_path JSON_PATH] [--now NOW]
[--past_depth_path PAST_DEPTH_PATH]
[--interval INTERVAL]
[--number_people_max NUMBER_PEOPLE_MAX]
[--reverse_specific REVERSE_SPECIFIC]
[--order_specific ORDER_SPECIFIC]
[--end_frame_no END_FRAME_NO]
[--order_start_frame ORDER_START_FRAME]
[--avi_output AVI_OUTPUT] [--verbose VERBOSE]
predict_video.py: error: unrecognized arguments: 5/1/_215002\zimzalabim_json 5/1/_215137
ERROR
Press any key to continue . . .

[errno-mmd]

It seems that the problem is caused by a difference in date format.
Would you try this pre-release version of motion_trace_bulk?
https://github.com/errno-mmd/motion_trace_bulk/archive/date_format.zip

[BaldyLLC]

I am still getting C:\Users\lewis.conda\envs\mmdmat\lib\site-packages\tensorflow\python\framework\dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
C:\Users\lewis.conda\envs\mmdmat\lib\site-packages\tensorflow\python\framework\dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
C:\Users\lewis.conda\envs\mmdmat\lib\site-packages\tensorflow\python\framework\dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
C:\Users\lewis.conda\envs\mmdmat\lib\site-packages\tensorflow\python\framework\dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
C:\Users\lewis.conda\envs\mmdmat\lib\site-packages\tensorflow\python\framework\dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
C:\Users\lewis.conda\envs\mmdmat\lib\site-packages\tensorflow\python\framework\dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
np_resource = np.dtype([("resource", np.ubyte, 1)])

[BaldyLLC]

nvm, it is working

[BaldyLLC]

now my code is looping with this
--- Logging error ---
Traceback (most recent call last):
File "C:\Users\lewis.conda\envs\mmdmat\lib\logging_init_.py", line 1028, in emit
stream.write(msg + self.terminator)
File "C:\Users\lewis.conda\envs\mmdmat\lib\encodings\cp1252.py", line 19, in encode
return codecs.charmap_encode(input,self.errors,encoding_table)[0]
UnicodeEncodeError: 'charmap' codec can't encode characters in position 0-3: character maps to
Call stack:
File "predict_video.py", line 783, in
main()
File "predict_video.py", line 777, in main
predict_video(now_str, opt.video_path, depth_path, past_depth_path, interval, opt.json_path, opt.number_people_max, reverse_specific_dict, order_specific_dict, is_avi_output, opt.end_frame_no, opt.order_start_frame, opt.verbose, opt)
File "predict_video.py", line 449, in predict_video
logger.warning("深度推定 idx: %s(%s) 処理: %s[sec]", _idx, cnt, time.time() - start)
Message: '深度推定 idx: %s(%s) 処理: %s[sec]'
Arguments: (900, 901, 107.13522481918335)
WARNING:main:深度推定 idx: 900(901) 処理: 107.13522481918335[sec]
DEBUG:main:cnt: 902, _idx: 901, flag: True, len(img_list): 1
DEBUG:main:cnt: 903, _idx: 902, flag: True, len(img_list): 2
DEBUG:main:cnt: 904, _idx: 903, flag: True, len(img_list): 3
DEBUG:main:cnt: 905, _idx: 904, flag: True, len(img_list): 4
DEBUG:main:cnt: 906, _idx: 905, flag: True, len(img_list): 5
DEBUG:main:cnt: 907, _idx: 906, flag: True, len(img_list): 6
DEBUG:main:cnt: 908, _idx: 907, flag: True, len(img_list): 7
DEBUG:main:cnt: 909, _idx: 908, flag: True, len(img_list): 8
DEBUG:main:cnt: 910, _idx: 909, flag: True, len(img_list): 9
DEBUG:main:cnt: 911, _idx: 910, flag: True, len(img_list): 10
DEBUG:main:cnt: 912, _idx: 911, flag: True, len(img_list): 11
DEBUG:main:cnt: 913, _idx: 912, flag: True, len(img_list): 12
DEBUG:main:cnt: 914, _idx: 913, flag: True, len(img_list): 13
DEBUG:main:cnt: 915, _idx: 914, flag: True, len(img_list): 14
DEBUG:main:cnt: 916, _idx: 915, flag: True, len(img_list): 15
DEBUG:main:cnt: 917, _idx: 916, flag: True, len(img_list): 16
DEBUG:main:cnt: 918, _idx: 917, flag: True, len(img_list): 17
DEBUG:main:cnt: 919, _idx: 918, flag: True, len(img_list): 18
DEBUG:main:cnt: 920, _idx: 919, flag: True, len(img_list): 19
DEBUG:main:cnt: 921, _idx: 920, flag: True, len(img_list): 20
DEBUG:main:========================= Video dataset #images = 20 =========
DEBUG:main.models.pix2pixdata_model:====================================== DIW NETWORK TRAIN FROM Ours_Bilinear=======================
DEBUG:main.models.pix2pixdata_model:===================Loading Pretrained Model OURS ===================================
DEBUG:main.models.pix2pixdata_model:---------- Networks initialized -------------
DEBUG:main.models.networks:HourglassModel(
(seq): Sequential(
(0): Conv2d(3, 128, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3))
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Channels4(
(list): ModuleList(
(0): Sequential(
(0): AvgPool2d(kernel_size=2, stride=2, padding=0)
(1): inception[[32], [3, 32, 32], [5, 32, 32], [7, 32, 32]]
(2): inception[[32], [3, 32, 32], [5, 32, 32], [7, 32, 32]]
(3): Channels3(
(list): ModuleList(
(0): Sequential(
(0): AvgPool2d(kernel_size=2, stride=2, padding=0)
(1): inception[[32], [3, 32, 32], [5, 32, 32], [7, 32, 32]]
(2): inception[[64], [3, 32, 64], [5, 32, 64], [7, 32, 64]]
(3): Channels2(
(list): ModuleList(
(0): Sequential(
(0): inception[[64], [3, 32, 64], [5, 32, 64], [7, 32, 64]]
(1): inception[[64], [3, 64, 64], [7, 64, 64], [11, 64, 64]]
)
(1): Sequential(
(0): AvgPool2d(kernel_size=2, stride=2, padding=0)
(1): inception[[64], [3, 32, 64], [5, 32, 64], [7, 32, 64]]
(2): inception[[64], [3, 32, 64], [5, 32, 64], [7, 32, 64]]
(3): Channels1(
(list): ModuleList(
(0): Sequential(
(0): inception[[64], [3, 32, 64], [5, 32, 64], [7, 32, 64]]
(1): inception[[64], [3, 32, 64], [5, 32, 64], [7, 32, 64]]
)
(1): Sequential(
(0): AvgPool2d(kernel_size=2, stride=2, padding=0)
(1): inception[[64], [3, 32, 64], [5, 32, 64], [7, 32, 64]]
(2): inception[[64], [3, 32, 64], [5, 32, 64], [7, 32, 64]]
(3): inception[[64], [3, 32, 64], [5, 32, 64], [7, 32, 64]]
(4): UpsamplingBilinear2d(scale_factor=2.0, mode=bilinear)
)
)
)
(4): inception[[64], [3, 32, 64], [5, 32, 64], [7, 32, 64]]
(5): inception[[64], [3, 64, 64], [7, 64, 64], [11, 64, 64]]
(6): UpsamplingBilinear2d(scale_factor=2.0, mode=bilinear)
)
)
)
(4): inception[[64], [3, 32, 64], [5, 32, 64], [7, 32, 64]]
(5): inception[[32], [3, 32, 32], [5, 32, 32], [7, 32, 32]]
(6): UpsamplingBilinear2d(scale_factor=2.0, mode=bilinear)
)
(1): Sequential(
(0): inception[[32], [3, 32, 32], [5, 32, 32], [7, 32, 32]]
(1): inception[[32], [3, 64, 32], [7, 64, 32], [11, 64, 32]]
)
)
)
(4): inception[[32], [3, 64, 32], [5, 64, 32], [7, 64, 32]]
(5): inception[[16], [3, 32, 16], [7, 32, 16], [11, 32, 16]]
(6): UpsamplingBilinear2d(scale_factor=2.0, mode=bilinear)
)
(1): Sequential(
(0): inception[[16], [3, 64, 16], [7, 64, 16], [11, 64, 16]]
)
)
)
)
(uncertainty_layer): Sequential(
(0): Conv2d(64, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): Sigmoid()
)
(pred_layer): Conv2d(64, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
)
DEBUG:main.models.networks:Total number of parameters: 5357730
DEBUG:main.models.pix2pixdata_model:-----------------------------------------------
DEBUG:main:================================= BEGIN VALIDATION =====================================
DEBUG:main:TESTING ON VIDEO