You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Jun 13, 2024. It is now read-only.
when I use !python3 pose_estimation/valid.py
--cfg experiments/coco/resnet50/256x192_d256x3_adam_lr1e-3.yaml
--flip-test
--model-file models/pytorch/pose_coco/pose_resnet_50_256x192.pth.tar
--workers 2
to valid the pretrained model,the following error happens!
=> classes: ['background', 'person']
=> num_images: 5000
=> load 6352 samples
=> fail to read data/coco/images/val2017/000000397133.jpg
Traceback (most recent call last):
File "pose_estimation/valid.py", line 168, in
=> fail to read data/coco/images/val2017/000000476258.jpg
main()
File "pose_estimation/valid.py", line 164, in main
final_output_dir, tb_log_dir)
File "/content/drive/MyDrive/simplepose /human-pose-estimation.pytorch/pose_estimation/../lib/core/function.py", line 108, in validate
for i, (input, target, target_weight, meta) in enumerate(val_loader):
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py", line 521, in next
data = self._next_data()
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py", line 1203, in _next_data
return self._process_data(data)
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py", line 1229, in _process_data
data.reraise()
File "/usr/local/lib/python3.7/dist-packages/torch/_utils.py", line 434, in reraise
raise exception
ValueError: Caught ValueError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
data = fetcher.fetch(index)
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py", line 49, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/content/drive/MyDrive/simplepose /human-pose-estimation.pytorch/pose_estimation/../lib/dataset/JointsDataset.py", line 80, in getitem
raise ValueError('Fail to read {}'.format(image_file))
ValueError: Fail to read data/coco/images/val2017/000000397133.jpg
The text was updated successfully, but these errors were encountered:
This error occurs when the code is unable to locate your image file.
I encountered this when using my own dataset. The best way to sort this out is to keep that particular image outside the Val/Train folder and run the code again. For example: for Valid images. Instead of placing them inside /data/images/valid2017. Just keep it /data/images and then try. Try with 1 image and see if the same error occurs for the next image of the valid. Then you would understand.
when I use !python3 pose_estimation/valid.py
--cfg experiments/coco/resnet50/256x192_d256x3_adam_lr1e-3.yaml
--flip-test
--model-file models/pytorch/pose_coco/pose_resnet_50_256x192.pth.tar
--workers 2
to valid the pretrained model,the following error happens!
=> classes: ['background', 'person']
=> num_images: 5000
=> load 6352 samples
=> fail to read data/coco/images/val2017/000000397133.jpg
Traceback (most recent call last):
File "pose_estimation/valid.py", line 168, in
=> fail to read data/coco/images/val2017/000000476258.jpg
main()
File "pose_estimation/valid.py", line 164, in main
final_output_dir, tb_log_dir)
File "/content/drive/MyDrive/simplepose /human-pose-estimation.pytorch/pose_estimation/../lib/core/function.py", line 108, in validate
for i, (input, target, target_weight, meta) in enumerate(val_loader):
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py", line 521, in next
data = self._next_data()
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py", line 1203, in _next_data
return self._process_data(data)
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py", line 1229, in _process_data
data.reraise()
File "/usr/local/lib/python3.7/dist-packages/torch/_utils.py", line 434, in reraise
raise exception
ValueError: Caught ValueError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
data = fetcher.fetch(index)
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py", line 49, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/content/drive/MyDrive/simplepose /human-pose-estimation.pytorch/pose_estimation/../lib/dataset/JointsDataset.py", line 80, in getitem
raise ValueError('Fail to read {}'.format(image_file))
ValueError: Fail to read data/coco/images/val2017/000000397133.jpg
The text was updated successfully, but these errors were encountered: