[INFO] ===== extracted torso and gt images =====
[INFO] ===== extract face landmarks from data/xx/ori_imgs =====
Traceback (most recent call last):
File "/home/xx/RAD-NeRF/data_utils/process.py", line 393, in
extract_landmarks(ori_imgs_dir)
File "/home/xx/RAD-NeRF/data_utils/process.py", line 50, in extract_landmarks
fa = face_alignment.FaceAlignment(face_alignment.LandmarksType.TWO_D, flip_input=False)
File "/home/xx/anaconda3/envs/RAD-NeRF/lib/python3.9/site-packages/face_alignment/api.py", line 78, in init
self.face_detector = face_detector_module.FaceDetector(device=device, verbose=verbose, face_detector_kwargs)
File "/home/xx/anaconda3/envs/RAD-NeRF/lib/python3.9/site-packages/face_alignment/detection/sfd/sfd_detector.py", line 24, in init
model_weights = load_url(models_urls['s3fd'])
File "/home/xx/anaconda3/envs/RAD-NeRF/lib/python3.9/site-packages/torch/hub.py", line 750, in load_state_dict_from_url
return torch.load(cached_file, map_location=map_location)
File "/home/xx/anaconda3/envs/RAD-NeRF/lib/python3.9/site-packages/torch/serialization.py", line 815, in load
return _legacy_load(opened_file, map_location, pickle_module, pickle_load_args)
File "/home/xx/anaconda3/envs/RAD-NeRF/lib/python3.9/site-packages/torch/serialization.py", line 1051, in _legacy_load
typed_storage._untyped_storage._set_from_file(
RuntimeError: unexpected EOF, expected 1021286 more bytes. The file might be corrupted.
the command is :python data_utils/process.py data//.mp4
the Video info shown below:
Metadata: major_brand : isom minor_version : 512 compatible_brands: isomiso2avc1mp41 comment : vid:v0300fg10000ciruiejc77u6d9t0l3p0 encoder : Lavf58.29.100 Stream #0:0(und): Video: mjpeg, yuvj420p(pc), 512x512 [SAR 9:16 DAR 9:16], q=1-31, 200 kb/s, 25 fps, 25 tbn, 25 tbc (default) Metadata: handler_name : VideoHandler encoder : Lavc58.54.100 mjpeg Side data: cpb: bitrate max/min/avg: 0/0/200000 buffer size: 0 vbv_delay: -1 frame= 3105 fps=756 q=1.0 Lsize=N/A time=00:02:04.20 bitrate=N/A speed=30.2x video:171048kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: unknown
the error detail is
[INFO] ===== extracted torso and gt images ===== [INFO] ===== extract face landmarks from data/xx/ori_imgs ===== Traceback (most recent call last): File "/home/xx/RAD-NeRF/data_utils/process.py", line 393, in
extract_landmarks(ori_imgs_dir)
File "/home/xx/RAD-NeRF/data_utils/process.py", line 50, in extract_landmarks
fa = face_alignment.FaceAlignment(face_alignment.LandmarksType.TWO_D, flip_input=False)
File "/home/xx/anaconda3/envs/RAD-NeRF/lib/python3.9/site-packages/face_alignment/api.py", line 78, in init
self.face_detector = face_detector_module.FaceDetector(device=device, verbose=verbose, face_detector_kwargs)
File "/home/xx/anaconda3/envs/RAD-NeRF/lib/python3.9/site-packages/face_alignment/detection/sfd/sfd_detector.py", line 24, in init
model_weights = load_url(models_urls['s3fd'])
File "/home/xx/anaconda3/envs/RAD-NeRF/lib/python3.9/site-packages/torch/hub.py", line 750, in load_state_dict_from_url
return torch.load(cached_file, map_location=map_location)
File "/home/xx/anaconda3/envs/RAD-NeRF/lib/python3.9/site-packages/torch/serialization.py", line 815, in load
return _legacy_load(opened_file, map_location, pickle_module, pickle_load_args)
File "/home/xx/anaconda3/envs/RAD-NeRF/lib/python3.9/site-packages/torch/serialization.py", line 1051, in _legacy_load
typed_storage._untyped_storage._set_from_file(
RuntimeError: unexpected EOF, expected 1021286 more bytes. The file might be corrupted.