microsoft
I have error to load image file in data/coco/images/val2017
I use python 3.6.
In step Valid on COCO val2017 using pretrained models, I did
sudo 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
and the error occurs
=> creating output/coco/pose_resnet_50/256x192_d256x3_adam_lr1e-3
=> creating log/coco/pose_resnet_50/256x192_d256x3_adam_lr1e-3_2019-01-14-10-45
Namespace(cfg='experiments/coco/resnet50/256x192_d256x3_adam_lr1e-3.yaml', coco_bbox_file=None, flip_test=True, frequent=100, gpus=None, model_file='models/pytorch/pose_coco/pose_resnet_50_256x192.pth.tar', post_process=False, shift_heatmap=False, use_detect_bbox=False, workers=None)
{'CUDNN': {'BENCHMARK': True, 'DETERMINISTIC': False, 'ENABLED': True},
'DATASET': {'DATASET': 'coco',
'DATA_FORMAT': 'jpg',
'FLIP': True,
'HYBRID_JOINTS_TYPE': '',
'ROOT': 'data/coco/',
'ROT_FACTOR': 40,
'SCALE_FACTOR': 0.3,
'SELECT_DATA': False,
'TEST_SET': 'val2017',
'TRAIN_SET': 'train2017'},
'DATA_DIR': '',
'DEBUG': {'DEBUG': True,
'SAVE_BATCH_IMAGES_GT': True,
'SAVE_BATCH_IMAGES_PRED': True,
'SAVE_HEATMAPS_GT': True,
'SAVE_HEATMAPS_PRED': True},
'GPUS': '0',
'LOG_DIR': 'log',
'LOSS': {'USE_TARGET_WEIGHT': True},
'MODEL': {'EXTRA': {'DECONV_WITH_BIAS': False,
'FINAL_CONV_KERNEL': 1,
'HEATMAP_SIZE': array([48, 64]),
'NUM_DECONV_FILTERS': [256, 256, 256],
'NUM_DECONV_KERNELS': [4, 4, 4],
'NUM_DECONV_LAYERS': 3,
'NUM_LAYERS': 50,
'SIGMA': 2,
'TARGET_TYPE': 'gaussian'},
'IMAGE_SIZE': array([192, 256]),
'INIT_WEIGHTS': True,
'NAME': 'pose_resnet',
'NUM_JOINTS': 17,
'PRETRAINED': 'models/pytorch/imagenet/resnet50-19c8e357.pth',
'STYLE': 'pytorch'},
'OUTPUT_DIR': 'output',
'PRINT_FREQ': 100,
'TEST': {'BATCH_SIZE': 32,
'BBOX_THRE': 1.0,
'COCO_BBOX_FILE': 'data/coco/person_detection_results/COCO_val2017_detections_AP_H_56_person.json',
'FLIP_TEST': True,
'IMAGE_THRE': 0.0,
'IN_VIS_THRE': 0.2,
'MODEL_FILE': 'models/pytorch/pose_coco/pose_resnet_50_256x192.pth.tar',
'NMS_THRE': 1.0,
'OKS_THRE': 0.9,
'POST_PROCESS': True,
'SHIFT_HEATMAP': True,
'USE_GT_BBOX': True},
'TRAIN': {'BATCH_SIZE': 32,
'BEGIN_EPOCH': 0,
'CHECKPOINT': '',
'END_EPOCH': 140,
'GAMMA1': 0.99,
'GAMMA2': 0.0,
'LR': 0.001,
'LR_FACTOR': 0.1,
'LR_STEP': [90, 120],
'MOMENTUM': 0.9,
'NESTEROV': False,
'OPTIMIZER': 'adam',
'RESUME': False,
'SHUFFLE': True,
'WD': 0.0001},
'WORKERS': 4}
=> loading model from models/pytorch/pose_coco/pose_resnet_50_256x192.pth.tar
/home/elysium/.local/lib/python3.6/site-packages/torch/nn/_reduction.py:49: UserWarning: size_average and reduce args will be deprecated, please use reduction='mean' instead.
warnings.warn(warning.format(ret))
loading annotations into memory...
Done (t=0.13s)
creating index...
index created!
=> classes: ['background', 'person']
=> num_images: 5000
=> load 6352 samples
=> fail to read data/coco/images/val2017/000000397133.jpg
=> fail to read data/coco/images/val2017/000000476258.jpg
=> fail to read data/coco/images/val2017/000000329323.jpg
=> fail to read data/coco/images/val2017/000000355257.jpg
=> fail to read data/coco/images/val2017/000000559842.jpg
=> fail to read data/coco/images/val2017/000000512836.jpg
=> fail to read data/coco/images/val2017/000000524456.jpg
=> fail to read data/coco/images/val2017/000000329219.jpg
=> fail to read data/coco/images/val2017/000000414170.jpg
Traceback (most recent call last):
File "pose_estimation/valid.py", line 165, in
I have image file "000000397133.jpg" in data/coco/images/val2017/000000397133.jpg. why this error occur?
My directory is look like this
same problem any solution?
Number of Layers Conv2d : 293 layers BatchNorm2d : 292 layers ReLU : 261 layers Bottleneck : 4 layers BasicBlock : 104 layers Upsample : 28 layers HighResolutionModule : 8 layers loading annotations into memory... Done (t=8.37s) creating index... index created! => classes: ['__background__', 'person'] => num_images: 118287 => load 149813 samples coco loading annotations into memory... Done (t=0.27s) creating index... index created! => classes: ['__background__', 'person'] => num_images: 5000 => load 6352 samples /usr/local/lib/python3.7/dist-packages/torch/optim/lr_scheduler.py:134: UserWarning: Detected call of lr_scheduler.step()beforeoptimizer.step(). In PyTorch 1.1.0 and later, you should call them in the opposite order: optimizer.step()beforelr_scheduler.step(). Failure to do this will result in PyTorch skipping the first value of the learning rate schedule. See more details at https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate "https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate", UserWarning) => fail to read /content/drive/MyDrive/deep-high-resolution-net/data/coco/images/train2017/000000414881.jpg Traceback (most recent call last): File "/content/drive/MyDrive/deep-high-resolution-net/tools/train.py", line 224, in <module> main() File "/content/drive/MyDrive/deep-high-resolution-net/tools/train.py", line 188, in main final_output_dir, tb_log_dir, writer_dict) File "/content/drive/MyDrive/deep-high-resolution-net/tools/../lib/core/function.py", line 38, in train for i, (input, target, target_weight, meta) in enumerate(train_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 <listcomp> data = [self.dataset[idx] for idx in possibly_batched_index] File "/content/drive/MyDrive/deep-high-resolution-net/tools/../lib/dataset/JointsDataset.py", line 135, in __getitem__ raise ValueError('Fail to read {}'.format(image_file)) ValueError: Fail to read /content/drive/MyDrive/deep-high-resolution-net/data/coco/images/train2017/000000414881.jpg
same problem any solution?
Number of Layers Conv2d : 293 layers BatchNorm2d : 292 layers ReLU : 261 layers Bottleneck : 4 layers BasicBlock : 104 layers Upsample : 28 layers HighResolutionModule : 8 layers loading annotations into memory... Done (t=8.37s) creating index... index created! => classes: ['__background__', 'person'] => num_images: 118287 => load 149813 samples coco loading annotations into memory... Done (t=0.27s) creating index... index created! => classes: ['__background__', 'person'] => num_images: 5000 => load 6352 samples /usr/local/lib/python3.7/dist-packages/torch/optim/lr_scheduler.py:134: UserWarning: Detected call oflr_scheduler.step()beforeoptimizer.step(). In PyTorch 1.1.0 and later, you should call them in the opposite order:optimizer.step()beforelr_scheduler.step(). Failure to do this will result in PyTorch skipping the first value of the learning rate schedule. See more details at https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate "https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate", UserWarning) => fail to read /content/drive/MyDrive/deep-high-resolution-net/data/coco/images/train2017/000000414881.jpg Traceback (most recent call last): File "/content/drive/MyDrive/deep-high-resolution-net/tools/train.py", line 224, in <module> main() File "/content/drive/MyDrive/deep-high-resolution-net/tools/train.py", line 188, in main final_output_dir, tb_log_dir, writer_dict) File "/content/drive/MyDrive/deep-high-resolution-net/tools/../lib/core/function.py", line 38, in train for i, (input, target, target_weight, meta) in enumerate(train_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 <listcomp> data = [self.dataset[idx] for idx in possibly_batched_index] File "/content/drive/MyDrive/deep-high-resolution-net/tools/../lib/dataset/JointsDataset.py", line 135, in __getitem__ raise ValueError('Fail to read {}'.format(image_file)) ValueError: Fail to read /content/drive/MyDrive/deep-high-resolution-net/data/coco/images/train2017/000000414881.jpg
Have you solved the problem yet? I meet the same problem now.
날짜: 2022.04.01 오후 09:34:41 (GMT+09:00) 제목: Re: [microsoft/human-pose-estimation.pytorch] I have error to load image file in data/coco/images/val2017 (#77)
same problem any solution? Number of Layers Conv2d : 293 layers BatchNorm2d : 292 layers ReLU : 261 layers Bottleneck : 4 layers BasicBlock : 104 layers Upsample : 28 layers HighResolutionModule : 8 layers loading annotations into memory... Done (t=8.37s) creating index... index created! => classes: ['background', 'person'] => num_images: 118287 => load 149813 samples coco loading annotations into memory... Done (t=0.27s) creating index... index created! => classes: ['background', 'person'] => num_images: 5000 => load 6352 samples /usr/local/lib/python3.7/dist-packages/torch/optim/lr_scheduler.py:134: UserWarning: Detected call of lr_scheduler.step()beforeoptimizer.step(). In PyTorch 1.1.0 and later, you should call them in the opposite order: optimizer.step()beforelr_scheduler.step(). Failure to do this will result in PyTorch skipping the first value of the learning rate schedule. See more details at https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate "https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate", UserWarning) => fail to read /content/drive/MyDrive/deep-high-resolution-net/data/coco/images/train2017/000000414881.jpg Traceback (most recent call last): File "/content/drive/MyDrive/deep-high-resolution-net/tools/train.py", line 224, in
Have you solved the problem yet? I meet the same problem now. — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>