search

pytorch / audio

Data manipulation and transformation for audio signal processing, powered by PyTorch
https://pytorch.org/audio
BSD 2-Clause "Simplified" License
2.43k stars 636 forks source link

_pickle.UnpicklingError: invalid load key, 'v'. #3711

Open YuQing2000 opened 7 months ago

YuQing2000 commented 7 months ago

🐛 Describe the bug

ISSUE

When I run python preprocess_lrs3.py --data-dir=D:/BaiduNetdiskDownload/LRS3 --detector=retinaface --dataset=lrs3 --root-dir=D:/pycharmProject/audio_vision/audio-main/examples/avsr/predata --subset=test --seg-duration=16 --groups=4 --job-index=0 The following appears D:\anaconda3\envs\davsr\lib\site-packages\torchaudio\backend\utils.py:62: UserWarning: No audio backend is available. warnings.warn("No audio backend is available.") Traceback (most recent call last): File "preprocess_lrs3.py", line 68, in <module> vid_dataloader = AVSRDataLoader(modality="video", detector=args.detector, resize=(96, 96)) File "D:\pycharmProject\audio_vision\audio-main\examples\avsr\data_prep\data\data_module.py", line 19, in __init__ self.landmarks_detector = LandmarksDetector(device="cuda:0") File "D:\pycharmProject\audio_vision\audio-main\examples\avsr\data_prep\detectors\retinaface\detector.py", line 17, in __init__ self.face_detector = RetinaFacePredictor( File "D:\pycharmProject\audio_vision\audio-main\examples\avsr\data_prep\face_detection\ibug\face_detection\retina_face\retina_face_predictor.py", line 28, in __init__ pretrained_dict = torch.load(model.weights, map_location=self.device) File "D:\anaconda3\envs\davsr\lib\site-packages\torch\serialization.py", line 795, in load return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args) File "D:\anaconda3\envs\davsr\lib\site-packages\torch\serialization.py", line 1002, in _legacy_load magic_number = pickle_module.load(f, **pickle_load_args) _pickle.UnpicklingError: invalid load key, 'v'. May I ask why this problem occurs? How to solve it

Versions

Collecting environment information... PyTorch version: 1.13.1 Is debug build: False CUDA used to build PyTorch: 11.7 ROCM used to build PyTorch: N/A

OS: Microsoft Windows 11 Home China GCC version: Could not collect Clang version: Could not collect CMake version: version 3.27.7 Libc version: N/A

Python version: 3.8.18 (default, Sep 11 2023, 13:39:12) [MSC v.1916 64 bit (AMD64)] (64-bit runtime) Python platform: Windows-10-10.0.22621-SP0 Is CUDA available: True CUDA runtime version: Could not collect CUDA_MODULE_LOADING set to: LAZY GPU models and configuration: GPU 0: NVIDIA GeForce RTX 3050 Laptop GPU Nvidia driver version: 517.18 cuDNN version: Could not collect HIP runtime version: N/A MIOpen runtime version: N/A Is XNNPACK available: True

CPU: Architecture=9 CurrentClockSpeed=1992 DeviceID=CPU0 Family=198 L2CacheSize=2048 L2CacheSpeed= Manufacturer=GenuineIntel MaxClockSpeed=1992 Name=Intel(R) Core(TM) i7-10700T CPU @ 2.00GHz ProcessorType=3 Revision=

Versions of relevant libraries: [pip3] numpy==1.24.3 [pip3] torch==1.13.1 [pip3] torchaudio==0.13.1 [pip3] torchvision==0.14.1 [conda] blas 1.0 mkl https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
[conda] mkl 2023.1.0 h6b88ed4_46358 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
[conda] mkl-service 2.4.0 py38h2bbff1b_1 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
[conda] mkl_fft 1.3.8 py38h2bbff1b_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
[conda] mkl_random 1.2.4 py38h59b6b97_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
[conda] numpy 1.24.3 py38h79a8e48_1 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
[conda] numpy-base 1.24.3 py38h8a87ada_1 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
[conda] pytorch 1.13.1 py3.8_cuda11.7_cudnn8_0 pytorch [conda] pytorch-cuda 11.7 h16d0643_5 pytorch [conda] pytorch-mutex 1.0 cuda pytorch [conda] torchaudio 0.13.1 pypi_0 pypi [conda] torchvision 0.14.1 pypi_0 pypi