config yml CPU CUDA

[sugatasanshiro]

when set to - cuda - gives this error

(venv) D:\liveportrait_talker>python inference.py --config_path config.yaml --source_path "D:\liveportrait_talker\Face\Tarkan1080.jpg" --audio_path "D:\liveportrait_talker\Audio\MyMemory.wav" --save_path "D:\liveportrait_talker\Output" Config File is loaded succesfully! Traceback (most recent call last): File "D:\liveportrait_talker\inference.py", line 78, in main(args) File "D:\liveportrait_talker\inference.py", line 23, in main preprocess = Preprocess(device=cfg.device, File "D:\liveportrait_talker\src\modules\preprocess.py", line 28, in init self.sd_prep = SadTalkerPreprocess(device=device, File "D:\liveportrait_talker\src\utils\preprocess\sadtalker_preprocess.py", line 20, in init self.detector = init_alignment_model('awing_fan', device=device, model_rootpath=model_path) File "D:\liveportrait_talker\src\utils\preprocess\helper.py", line 147, in init_alignment_model model.load_state_dict(torch.load(model_path, map_location=device)['state_dict'], strict=True) File "D:\liveportrait_talker\venv\lib\site-packages\torch\serialization.py", line 1040, in load return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args) File "D:\liveportrait_talker\venv\lib\site-packages\torch\serialization.py", line 1272, in _legacy_load result = unpickler.load() File "D:\liveportrait_talker\venv\lib\site-packages\torch\serialization.py", line 1205, in persistent_load obj = restore_location(obj, location) File "D:\liveportrait_talker\venv\lib\site-packages\torch\serialization.py", line 1313, in restore_location return default_restore_location(storage, map_location) File "D:\liveportrait_talker\venv\lib\site-packages\torch\serialization.py", line 393, in default_restore_location raise RuntimeError("don't know how to restore data location of " RuntimeError: don't know how to restore data location of torch.storage.UntypedStorage (tagged with gpu)

when set to - cpu - this error

(venv) D:\liveportrait_talker>python inference.py --config_path config.yaml --source_path "D:\liveportrait_talker\Face\Tarkan1080.jpg" --audio_path "D:\liveportrait_talker\Audio\MyMemory.wav" --save_path "D:\liveportrait_talker\Output" Config File is loaded succesfully! D:\liveportrait_talker\venv\lib\site-packages\torchvision\models_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. warnings.warn( D:\liveportrait_talker\venv\lib\site-packages\torchvision\models_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing weights=None. warnings.warn(msg) Downloading: "https://github.com/xinntao/facexlib/releases/download/v0.1.0/detection_Resnet50_Final.pth" to D:\liveportrait_talker\pretrained_models\sadtalker\detection_Resnet50_Final.pth

100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 104M/104M [01:19<00:00, 1.37MB/s] Traceback (most recent call last): File "D:\liveportrait_talker\inference.py", line 78, in main(args) File "D:\liveportrait_talker\inference.py", line 23, in main preprocess = Preprocess(device=cfg.device, File "D:\liveportrait_talker\src\modules\preprocess.py", line 31, in init self.load_3dmm_coeff_model(sadtalker_checkpoint_path=sadtalker_checkpoint_path) File "D:\liveportrait_talker\src\modules\preprocess.py", line 34, in load_3dmm_coeff_model checkpoint = safetensors.torch.load_file(sadtalker_checkpoint_path) File "D:\liveportrait_talker\venv\lib\site-packages\safetensors\torch.py", line 259, in load_file with safe_open(filename, framework="pt", device=device) as f:

[mkara44]

Did you download the pretrained models?

[sugatasanshiro]

yes, now it gives this error

(venv) D:\liveportrait_talker>python inference.py --config_path config.yaml --source_path "D:\liveportrait_talker\Face\Tarkan1080.jpg" --audio_path "D:\liveportrait_talker\Audio\MyMemory.wav" --save_path "D:\liveportrait_talker\Output" Config File is loaded succesfully! D:\liveportrait_talker\venv\lib\site-packages\torchvision\models_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. warnings.warn( D:\liveportrait_talker\venv\lib\site-packages\torchvision\models_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing weights=None. warnings.warn(msg) Traceback (most recent call last): File "D:\liveportrait_talker\inference.py", line 78, in main(args) File "D:\liveportrait_talker\inference.py", line 34, in main map2lp = Map2LivePortrait(device=cfg.device, File "D:\liveportrait_talker\src\modules\map2lp.py", line 13, in init self.mapping.load_state_dict(torch.load(mappingnet_model_path)) File "D:\liveportrait_talker\venv\lib\site-packages\torch\serialization.py", line 1025, in load return _load(opened_zipfile, File "D:\liveportrait_talker\venv\lib\site-packages\torch\serialization.py", line 1446, in _load result = unpickler.load() File "D:\liveportrait_talker\venv\lib\site-packages\torch\serialization.py", line 1416, in persistent_load typed_storage = load_tensor(dtype, nbytes, key, _maybe_decode_ascii(location)) File "D:\liveportrait_talker\venv\lib\site-packages\torch\serialization.py", line 1390, in load_tensor wrap_storage=restore_location(storage, location), File "D:\liveportrait_talker\venv\lib\site-packages\torch\serialization.py", line 390, in default_restore_location result = fn(storage, location) File "D:\liveportrait_talker\venv\lib\site-packages\torch\serialization.py", line 307, in _mps_deserialize return obj.mps() File "D:\liveportraittalker\venv\lib\site-packages\torch\storage.py", line 144, in mps return torch.UntypedStorage(self.size(), device="mps").copy(self, False) RuntimeError: torch.UntypedStorage(): Storage device not recognized: mps

(venv) D:\liveportrait_talker>

[sugatasanshiro]

i installed pytorch with command

install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118

but - requirements.txt - is uninstalling it