DinoMan / speech-driven-animation

949 stars 289 forks source link

To run an error #58

Open cc-qing opened 3 years ago

cc-qing commented 3 years ago

Traceback (most recent call last): File "test.py", line 5, in va = sda.VideoAnimator() File "/Users/zego/speech-driven-animation-no_torchaudio_dependency/sda/sda.py", line 106, in init self.fa = face_alignment.FaceAlignment(face_alignment.LandmarksType._2D, device="cpu", flip_input=False) File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/face_alignment-1.1.1-py3.8.egg/face_alignment/api.py", line 69, in init self.face_detector = face_detector_module.FaceDetector(device=device, verbose=verbose) File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/face_alignment-1.1.1-py3.8.egg/face_alignment/detection/sfd/sfd_detector.py", line 22, in init model_weights = load_url(models_urls['s3fd']) File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/torch-1.6.0-py3.8-macosx-10.9-x86_64.egg/torch/hub.py", line 495, in load_state_dict_from_url return torch.load(cached_file, map_location=map_location) File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/torch-1.6.0-py3.8-macosx-10.9-x86_64.egg/torch/serialization.py", line 585, in load return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args) File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/torch-1.6.0-py3.8-macosx-10.9-x86_64.egg/torch/serialization.py", line 772, in _legacy_load deserialized_objects[key]._set_from_file(f, offset, f_should_read_directly) RuntimeError: unexpected EOF, expected 5182726 more bytes. The file might be corrupted. Python(35107,0x10f700dc0) malloc: Incorrect checksum for freed object 0x7fd3bc9557f8: probably modified after being freed. Corrupt value: 0x3fffffffffffffff Python(35107,0x10f700dc0) malloc: *** set a breakpoint in malloc_error_break to debug Abort trap: 6