A flexible and extensible framework for gait recognition. You can focus on designing your own models and comparing with state-of-the-arts easily with the help of OpenGait.
Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
[2024-03-28 13:18:44] [INFO]: {'enable_float16': True, 'restore_ckpt_strict': True, 'restore_hint': 0, 'save_name': 'GaitBase', 'eval_func': 'evaluate_indoor_dataset', 'sampler': {'batch_size': 16, 'sample_type': 'all_ordered', 'type': 'InferenceSampler', 'batch_shuffle': False, 'frames_all_limit': 720}, 'transform': [{'type': 'BaseSilCuttingTransform'}], 'metric': 'euc', 'cross_view_gallery': False}
[2024-03-28 13:18:44] [INFO]: {'model': 'mymodel', 'backbone_cfg': {'type': 'ResNet9', 'block': 'BasicBlock', 'channels': [64, 128, 256, 512], 'layers': [1, 1, 1, 1], 'strides': [1, 2, 2, 1], 'maxpool': False}, 'SeparateFCs': {'in_channels': 512, 'out_channels': 256, 'parts_num': 15}, 'SeparateBNNecks': {'class_num': 5153, 'in_channels': 256, 'parts_num': 15}, 'bin_num': [16]}
[2024-03-28 13:18:44] [INFO]: {'dataset_name': 'OUMVLP', 'dataset_root': '/home/xyq/dataset/OUMVLP_pkl/', 'num_workers': 1, 'dataset_partition': './datasets/OUMVLP/OUMVLP.json', 'remove_no_gallery': False, 'cache': False, 'test_dataset_name': 'OUMVLP'}
[2024-03-28 13:18:46] [INFO]: -------- Test Pid List --------
[2024-03-28 13:18:46] [INFO]: [00002, 00004, ..., 10307]
[2024-03-28 13:18:51] [INFO]: Parameters Count: 26.92090M
[2024-03-28 13:18:51] [INFO]: Model Initialization Finished!
Transforming: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 129292/129292 [43:03<00:00, 50.04it/s]
Traceback (most recent call last):
File "/home/xyq/xyqcode/OpenGait/opengait/main.py", line 77, in
run_model(cfgs, training)
File "/home/xyq/xyqcode/OpenGait/opengait/main.py", line 60, in run_model
Model.run_test(model)
File "/home/xyq/xyqcode/OpenGait/opengait/modeling/base_model.py", line 465, in run_test
return eval_func(info_dict, dataset_name, **valid_args)
File "/home/xyq/xyqcode/OpenGait/opengait/evaluation/evaluator.py", line 144, in evaluate_indoor_dataset
return single_view_gallery_evaluation(
File "/home/xyq/xyqcode/OpenGait/opengait/evaluation/evaluator.py", line 114, in single_view_gallery_evaluation
idx = dist.topk(num_rank, largest=False)[1].cpu().numpy()
RuntimeError: selected index k out of range
(pytorch) -bash-5.1# TORCH_DISTRIBUTED_DEBUG=DETAIL CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.run --nproc_per_node=2 opengait/main.py --cfgs ./configs/gaitbase/gaitbase_oumvlp.yaml --phase test --iter 0 WARNING:main:
Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
[2024-03-28 13:18:44] [INFO]: {'enable_float16': True, 'restore_ckpt_strict': True, 'restore_hint': 0, 'save_name': 'GaitBase', 'eval_func': 'evaluate_indoor_dataset', 'sampler': {'batch_size': 16, 'sample_type': 'all_ordered', 'type': 'InferenceSampler', 'batch_shuffle': False, 'frames_all_limit': 720}, 'transform': [{'type': 'BaseSilCuttingTransform'}], 'metric': 'euc', 'cross_view_gallery': False} [2024-03-28 13:18:44] [INFO]: {'model': 'mymodel', 'backbone_cfg': {'type': 'ResNet9', 'block': 'BasicBlock', 'channels': [64, 128, 256, 512], 'layers': [1, 1, 1, 1], 'strides': [1, 2, 2, 1], 'maxpool': False}, 'SeparateFCs': {'in_channels': 512, 'out_channels': 256, 'parts_num': 15}, 'SeparateBNNecks': {'class_num': 5153, 'in_channels': 256, 'parts_num': 15}, 'bin_num': [16]} [2024-03-28 13:18:44] [INFO]: {'dataset_name': 'OUMVLP', 'dataset_root': '/home/xyq/dataset/OUMVLP_pkl/', 'num_workers': 1, 'dataset_partition': './datasets/OUMVLP/OUMVLP.json', 'remove_no_gallery': False, 'cache': False, 'test_dataset_name': 'OUMVLP'} [2024-03-28 13:18:46] [INFO]: -------- Test Pid List -------- [2024-03-28 13:18:46] [INFO]: [00002, 00004, ..., 10307] [2024-03-28 13:18:51] [INFO]: Parameters Count: 26.92090M [2024-03-28 13:18:51] [INFO]: Model Initialization Finished! Transforming: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 129292/129292 [43:03<00:00, 50.04it/s] Traceback (most recent call last): File "/home/xyq/xyqcode/OpenGait/opengait/main.py", line 77, in
run_model(cfgs, training)
File "/home/xyq/xyqcode/OpenGait/opengait/main.py", line 60, in run_model
Model.run_test(model)
File "/home/xyq/xyqcode/OpenGait/opengait/modeling/base_model.py", line 465, in run_test
return eval_func(info_dict, dataset_name, **valid_args)
File "/home/xyq/xyqcode/OpenGait/opengait/evaluation/evaluator.py", line 144, in evaluate_indoor_dataset
return single_view_gallery_evaluation(
File "/home/xyq/xyqcode/OpenGait/opengait/evaluation/evaluator.py", line 114, in single_view_gallery_evaluation
idx = dist.topk(num_rank, largest=False)[1].cpu().numpy()
RuntimeError: selected index k out of range