AssafSinger94 / dino-tracker

Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video”
MIT License
416 stars 40 forks source link

'/data/yubowen/dino-tracker/dataset/horsejump/video/dino_embeddings/dino_embed_video-layer=23.pt' #37

Open xiyangyang99 opened 1 week ago

xiyangyang99 commented 1 week ago

Using the horsejump dataset, after running main_preprocessing. py, only the of_trajections folder was generated and the dinoubest-buddes and dinoueembeddings folders in the readme file were not generated。 The output log is: (omhand) [yubw@gpu1 dino-tracker]$ python main_preprocessing.py --config ./config/preprocessing.yaml --data-path /data/yubowen/dino-tracker/dataset/horsejump/video ----- Running python ./extract_trajectories.py --frames-path /data/yubowen/dino-tracker/dataset/horsejump/video/video --output-path /data/yubowen/dino-tracker/dataset/horsejump/video/of_trajectories/trajectories.pt --min-trajectory-length 2 --threshold 1.5 --infer-res-size 476 854 --filter-using-direct-flow --direct-flow-threshold 2.5 Namespace(frames_path='/data/yubowen/dino-tracker/dataset/horsejump/video/video', output_path='/data/yubowen/dino-tracker/dataset/horsejump/video/of_trajectories/trajectories.pt', infer_res_size=[476, 854], threshold=1.5, min_trajectory_length=2, filter_using_direct_flow=True, direct_flow_threshold=2.5) XXXXXXXXXXXXXXXXXX /data/yubowen/dino-tracker/dataset/horsejump/video/video Traceback (most recent call last): File "/data/yubowen/dino-tracker/./extract_trajectories.py", line 283, in save_trajectories(args) File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, kwargs) File "/data/yubowen/dino-tracker/./extract_trajectories.py", line 186, in save_trajectories masks, flows = get_flows_with_masks( File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, *kwargs) File "/data/yubowen/dino-tracker/./extract_trajectories.py", line 45, in get_flows_with_masks flows = torch.zeros((2, len(images) - 1, 2, h, w), device=device) RuntimeError: Trying to create tensor with negative dimension -1: [2, -1, 2, 476, 854] ----- Running python ./save_dino_embed_video.py --data-path /data/yubowen/dino-tracker/dataset/horsejump/video --config ./config/preprocessing.yaml Traceback (most recent call last): File "/data/yubowen/dino-tracker/./save_dino_embed_video.py", line 35, in save_dino_embed_video(args) File "/data/yubowen/dino-tracker/./save_dino_embed_video.py", line 20, in save_dino_embed_video video = load_video(video_folder=video_folder, resize=(h, w), num_frames=400).to(device) # T x 3 x H x W File "/data/yubowen/dino-tracker/data/data_utils.py", line 104, in load_video return torch.stack(video) RuntimeError: stack expects a non-empty TensorList ----- Running python ./save_dino_embed_video.py --data-path /data/yubowen/dino-tracker/dataset/horsejump/video --config ./config/preprocessing.yaml --for-mask Traceback (most recent call last): File "/data/yubowen/dino-tracker/./save_dino_embed_video.py", line 35, in save_dino_embed_video(args) File "/data/yubowen/dino-tracker/./save_dino_embed_video.py", line 20, in save_dino_embed_video video = load_video(video_folder=video_folder, resize=(h, w), num_frames=400).to(device) # T x 3 x H x W File "/data/yubowen/dino-tracker/data/data_utils.py", line 104, in load_video return torch.stack(video) RuntimeError: stack expects a non-empty TensorList ----- Running python ./create_fg_mask.py --dino-embed-video-path /data/yubowen/dino-tracker/dataset/horsejump/video/dino_embeddings/dino_embed_video-layer=23.pt --h 476 --w 854 --mask-path /data/yubowen/dino-tracker/dataset/horsejump/video/masks --fg_mask_threshold 0.6 Traceback (most recent call last): File "/data/yubowen/dino-tracker/./create_fg_mask.py", line 72, in run(args) File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(args, kwargs) File "/data/yubowen/dino-tracker/./create_fg_mask.py", line 52, in run dino_embed_video = torch.load(args.dino_embed_video_path) # T x C x H x W File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/serialization.py", line 998, in load with _open_file_like(f, 'rb') as opened_file: File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/serialization.py", line 445, in _open_file_like return _open_file(name_or_buffer, mode) File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/serialization.py", line 426, in init super().init(open(name, mode)) FileNotFoundError: [Errno 2] No such file or directory: '/data/yubowen/dino-tracker/dataset/horsejump/video/dino_embeddings/dino_embed_video-layer=23.pt' ----- Running python ./split_trajectories_to_fg_bg.py --traj_path /data/yubowen/dino-tracker/dataset/horsejump/video/of_trajectories/trajectories.pt --fg_masks_path /data/yubowen/dino-tracker/dataset/horsejump/video/masks --fg_traj_path /data/yubowen/dino-tracker/dataset/horsejump/video/of_trajectories/fg_trajectories.pt --bg_traj_path /data/yubowen/dino-tracker/dataset/horsejump/video/of_trajectories/bg_trajectories.pt Traceback (most recent call last): File "/data/yubowen/dino-tracker/./split_trajectories_to_fg_bg.py", line 95, in split_trajectories_to_fg_bg(args) File "/data/yubowen/dino-tracker/./split_trajectories_to_fg_bg.py", line 81, in split_trajectories_to_fg_bg mask_filter_trajectories(args.traj_path, args.fg_masks_path, args.fg_traj_path, filter_bg=False) File "/data/yubowen/dino-tracker/./split_trajectories_to_fg_bg.py", line 56, in mask_filter_trajectories trajectories = torch.load(traj_path, map_location="cpu") File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/serialization.py", line 998, in load with _open_file_like(f, 'rb') as opened_file: File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/serialization.py", line 445, in _open_file_like return _open_file(name_or_buffer, mode) File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/serialization.py", line 426, in init super().init(open(name, mode)) FileNotFoundError: [Errno 2] No such file or directory: '/data/yubowen/dino-tracker/dataset/horsejump/video/of_trajectories/trajectories.pt' ----- Running python ./main_dino_bb_preprocessing.py --config ./config/preprocessing.yaml --data-path /data/yubowen/dino-tracker/dataset/horsejump/video ----- Running python ./extract_dino_best_buddies.py --dino-emb-path /data/yubowen/dino-tracker/dataset/horsejump/video/dino_embeddings/dino_embed_video.pt --stride 7 --out-path /data/yubowen/dino-tracker/dataset/horsejump/video/dino_best_buddies/dino_best_buddies.pt --h 476 --w 854 /home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/functional.py:507: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3549.) return _VF.meshgrid(tensors, kwargs) # type: ignore[attr-defined] Traceback (most recent call last): File "/data/yubowen/dino-tracker/./extract_dino_best_buddies.py", line 65, in run(args) File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, *kwargs) File "/data/yubowen/dino-tracker/./extract_dino_best_buddies.py", line 21, in run features = torch.load(dino_embed_video_path) # T x C x H x W File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/serialization.py", line 998, in load with _open_file_like(f, 'rb') as opened_file: File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/serialization.py", line 445, in _open_file_like return _open_file(name_or_buffer, mode) File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/serialization.py", line 426, in init super().init(open(name, mode)) FileNotFoundError: [Errno 2] No such file or directory: '/data/yubowen/dino-tracker/dataset/horsejump/video/dino_embeddings/dino_embed_video.pt' ----- Running python ./extract_trajectories.py --frames-path /data/yubowen/dino-tracker/dataset/horsejump/video/video --output-path /data/yubowen/dino-tracker/dataset/horsejump/video/of_trajectories/trajectories_wo_direct_filter.pt --min-trajectory-length 2 --threshold 1.5 --infer-res-size 476 854 Namespace(frames_path='/data/yubowen/dino-tracker/dataset/horsejump/video/video', output_path='/data/yubowen/dino-tracker/dataset/horsejump/video/of_trajectories/trajectories_wo_direct_filter.pt', infer_res_size=[476, 854], threshold=1.5, min_trajectory_length=2, filter_using_direct_flow=False, direct_flow_threshold=None) XXXXXXXXXXXXXXXXXX /data/yubowen/dino-tracker/dataset/horsejump/video/video Traceback (most recent call last): File "/data/yubowen/dino-tracker/./extract_trajectories.py", line 283, in save_trajectories(args) File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(args, kwargs) File "/data/yubowen/dino-tracker/./extract_trajectories.py", line 186, in save_trajectories masks, flows = get_flows_with_masks( File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, *kwargs) File "/data/yubowen/dino-tracker/./extract_trajectories.py", line 45, in get_flows_with_masks flows = torch.zeros((2, len(images) - 1, 2, h, w), device=device) RuntimeError: Trying to create tensor with negative dimension -1: [2, -1, 2, 476, 854] ----- Running python ./of_filter_dino_best_buddies.py --dino-bb-path /data/yubowen/dino-tracker/dataset/horsejump/video/dino_best_buddies/dino_best_buddies.pt --traj-path /data/yubowen/dino-tracker/dataset/horsejump/video/of_trajectories/trajectories_wo_direct_filter.pt --out-path /data/yubowen/dino-tracker/dataset/horsejump/video/dino_best_buddies/dino_best_buddies_filtered.pt --dino-bb-stride 7 --h 476 --w 854 Traceback (most recent call last): File "/data/yubowen/dino-tracker/./of_filter_dino_best_buddies.py", line 124, in run(args) File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(args, **kwargs) File "/data/yubowen/dino-tracker/./of_filter_dino_best_buddies.py", line 45, in run bb_data = torch.load(dino_bb_path) File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/serialization.py", line 998, in load with _open_file_like(f, 'rb') as opened_file: File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/serialization.py", line 445, in _open_file_like return _open_file(name_or_buffer, mode) File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/serialization.py", line 426, in init super().init(open(name, mode)) FileNotFoundError: [Errno 2] No such file or directory: '/data/yubowen/dino-tracker/dataset/horsejump/video/dino_best_buddies/dino_best_buddies.pt' ----- Running python ./compute_dino_bb_nms.py --dino-bb-path /data/yubowen/dino-tracker/dataset/horsejump/video/dino_best_buddies/dino_best_buddies_filtered.pt --dino-emb-path /data/yubowen/dino-tracker/dataset/horsejump/video/dino_embeddings/dino_embed_video.pt --out-path /data/yubowen/dino-tracker/dataset/horsejump/video/dino_best_buddies/dino_best_buddies_filtered.pt --stride 7 --box-size 30 --iou-thresh 0.2 Traceback (most recent call last): File "/data/yubowen/dino-tracker/./compute_dino_bb_nms.py", line 122, in run(args) File "/data/yubowen/dino-tracker/./compute_dino_bb_nms.py", line 82, in run dino_bb = torch.load(args.dino_bb_path) # { 'i_j': { source_coords: [N x 2] } } File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/serialization.py", line 998, in load with _open_file_like(f, 'rb') as opened_file: File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/serialization.py", line 445, in _open_file_like return _open_file(name_or_buffer, mode) File "/home/yubw/miniconda3/envs/omhand/lib/python3.10/site-packages/torch/serialization.py", line 426, in init super().init(open(name, mode)) FileNotFoundError: [Errno 2] No such file or directory: '/data/yubowen/dino-tracker/dataset/horsejump/video/dino_best_buddies/dino_best_buddies_filtered.pt'

Erze-ee commented 4 days ago

I have the same question , so how to get '.pt' files.