Fictionarry / ER-NeRF

[ICCV'23] Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis
https://fictionarry.github.io/ER-NeRF/
MIT License
1.07k stars 137 forks source link

训练时候遇到以下报错,怎么解决 #159

Open zhangshulin12 opened 3 months ago

zhangshulin12 commented 3 months ago

Traceback (most recent call last): File "E:\oyh\ER-NeRF-main\data_utils\face_parsing\test.py", line 98, in evaluate(respth=args.respath, dspth=args.imgpath, cp=args.modelpath) File "E:\oyh\ER-NeRF-main\data_utils\face_parsing\test.py", line 62, in evaluate net.load_state_dict(torch.load(cp)) File "E:\oyh\Anaconda\envs\nerfstream\lib\site-packages\torch\serialization.py", line 699, in load with _open_file_like(f, 'rb') as opened_file: File "E:\oyh\Anaconda\envs\nerfstream\lib\site-packages\torch\serialization.py", line 230, in _open_file_like return _open_file(name_or_buffer, mode) File "E:\oyh\Anaconda\envs\nerfstream\lib\site-packages\torch\serialization.py", line 211, in init super(_open_file, self).init(open(name, mode)) FileNotFoundError: [Errno 2] No such file or directory: 'data_utils/face_parsing/79999_iter.pth' [INFO] ===== extracted semantics ===== [INFO] ===== extract background image from E:/oyh/ER-NeRF-main/data/xuniren\oriimgs ===== 0%| | 0/95 [00:00<?, ?it/s][ WARN:0@737.110] global loadsave.cpp:241 cv::findDecoder imread('E:/oyh/ER-NeRF-main/data/xuniren\parsing\0.png'): can't open/read file: check file path/integrity 0%| | 0/95 [00:00<?, ?it/s] Traceback (most recent call last): File "E:\oyh\ER-NeRF-main\data_utils\process.py", line 388, in extract_background(base_dir, ori_imgs_dir) File "E:\oyh\ER-NeRF-main\data_utils\process.py", line 84, in extract_background bg = (parse_img[..., 0] == 255) & (parse_img[..., 1] == 255) & (parse_img[..., 2] == 255) TypeError: 'NoneType' object is not subscriptable

kiligzn commented 2 months ago

我也遇到了这个问题,请问你解决了吗