[extract flow] FileNotFoundError: [Errno 2] No such file or directory: 'data/xxx\\flow_result\\2_1.npy'

[linhcentrio]

[INFO] ===== extract flow =====
num data: 7667
load done
0%| | 0/7667 [00:00<?, ?it/s]D:\Talking_head\SyncTalk\venv\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\TensorShape.cpp:3484.)
return VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
74%|█████████████████████████████████████████████████████████▊ | 5685/7667 [17:12<06:00, 5.51it/s]
Traceback (most recent call last):
File "D:\Talking_head\SyncTalk\data_utils\UNFaceFlow\test_flow.py", line 62, in
predict(data)
File "D:\Talking_head\SyncTalk\data_utils\UNFaceFlow\test_flow.py", line 34, in predict
save_flow_numpy(os.path.join(save_path, os.path.basename(
File "D:\Talking_head\SyncTalk\data_utils\UNFaceFlow\test_flow.py", line 17, in save_flow_numpy
np.save(filename, flow_input)
File "<array_function internals>", line 200, in save
File "D:\Talking_head\SyncTalk\venv\lib\site-packages\numpy\lib\npyio.py", line 522, in save
format.write_array(fid, arr, allow_pickle=allow_pickle,
File "D:\Talking_head\SyncTalk\venv\lib\site-packages\numpy\lib\format.py", line 723, in write_array
array.tofile(fp)
OSError: 1843200 requested and 0 written
Traceback (most recent call last):
File "D:\Talking_head\SyncTalk\data_utils\process.py", line 477, in
extract_flow(base_dir, ori_imgs_dir, mask_imgs_dir, flow_dir)
File "D:\Talking_head\SyncTalk\data_utils\process.py", line 295, in extract_flow
flow = np.load(os.path.join(flow_dir, '{:d}{:d}.npy'.format(ref_id, valid_img_ids[i])))
File "D:\Talking_head\SyncTalk\venv\lib\site-packages\numpy\lib\npyio.py", line 405, in load
fid = stack.enter_context(open(os_fspath(file), "rb"))
FileNotFoundError: [Errno 2] No such file or directory: 'data/Mr_Dung\flow_result\2_1.npy'

[Eikwang]

需要将数据集中的wav音频转化为npy文件