Closed happy-jihye closed 2 years ago
Hello, ZLH Thank you for you great implementation.
Would you mind providing the pretrained models (checkpoints)? Thank you for your help.
Jihye 😊
At present, I am trying to train the model on voxceleb2 and other datasets with higher resolutions (e.g. > 512x512). After that, I will choose some checkpoints with better performance to release.
I can't get anywhere without that file it seems.
no checkpoint
(torch) ➜ One-Shot_Free-View_Neural_Talking_Head_Synthesis git:(main) ✗ python demo.py --config config/vox-256.yaml --source_image '/home/jp/Desktop/2.jpg' --driving_video '/home/jp/Documents/gitWorkspace/SimSwap/J11-wm.mp4' --relative --adapt_scale --find_best_frame
demo.py:28: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
config = yaml.load(f)
Traceback (most recent call last):
File "demo.py", line 282, in <module>
generator, kp_detector, he_estimator = load_checkpoints(config_path=opt.config, checkpoint_path=opt.checkpoint, cpu=opt.cpu)
File "demo.py", line 48, in load_checkpoints
checkpoint = torch.load(checkpoint_path)
File "/home/jp/miniconda3/envs/torch/lib/python3.8/site-packages/torch/serialization.py", line 579, in load
with _open_file_like(f, 'rb') as opened_file:
File "/home/jp/miniconda3/envs/torch/lib/python3.8/site-packages/torch/serialization.py", line 230, in _open_file_like
return _open_file(name_or_buffer, mode)
File "/home/jp/miniconda3/envs/torch/lib/python3.8/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: ''
made up check point. (file doesn't exist)
(torch) ➜ One-Shot_Free-View_Neural_Talking_Head_Synthesis git:(main) ✗ python demo.py --config config/vox-256.yaml --checkpoint ./check.pt --source_image '/home/jp/Desktop/2.jpg' --driving_video '/home/jp/Documents/gitWorkspace/SimSwap/J11-wm.mp4' --relative --adapt_scale --find_best_frame
demo.py:28: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
config = yaml.load(f)
Traceback (most recent call last):
File "demo.py", line 282, in <module>
generator, kp_detector, he_estimator = load_checkpoints(config_path=opt.config, checkpoint_path=opt.checkpoint, cpu=opt.cpu)
File "demo.py", line 48, in load_checkpoints
checkpoint = torch.load(checkpoint_path)
File "/home/jp/miniconda3/envs/torch/lib/python3.8/site-packages/torch/serialization.py", line 579, in load
with _open_file_like(f, 'rb') as opened_file:
File "/home/jp/miniconda3/envs/torch/lib/python3.8/site-packages/torch/serialization.py", line 230, in _open_file_like
return _open_file(name_or_buffer, mode)
File "/home/jp/miniconda3/envs/torch/lib/python3.8/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: './check.pt'
I didn‘t provide the pre-trained model,so you have to train the model first to get the checkpoint.
来自钉钉专属商务邮箱------------------------------------------------------------------ 发件人:John D. @.> 日 期:2021年09月05日 01:56:03 @.> @.>; @.> 主 题:Re: [zhanglonghao1992/One-Shot_Free-View_Neural_Talking_Head_Synthesis] checkpoint (pretrained model) (#4)
I can't get anywhere without that file it seems. no checkpoint (torch) ➜ One-Shot_Free-View_Neural_Talking_Head_Synthesis git:(main) ✗ python demo.py --config config/vox-256.yaml --source_image '/home/jp/Desktop/2.jpg' --driving_video '/home/jp/Documents/gitWorkspace/SimSwap/J11-wm.mp4' --relative --adapt_scale --find_best_frame
demo.py:28: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
config = yaml.load(f)
Traceback (most recent call last):
File "demo.py", line 282, in
generator, kp_detector, he_estimator = load_checkpoints(config_path=opt.config, checkpoint_path=opt.checkpoint, cpu=opt.cpu)
File "demo.py", line 48, in load_checkpoints
checkpoint = torch.load(checkpoint_path)
File "/home/jp/miniconda3/envs/torch/lib/python3.8/site-packages/torch/serialization.py", line 579, in load
with _open_file_like(f, 'rb') as opened_file:
File "/home/jp/miniconda3/envs/torch/lib/python3.8/site-packages/torch/serialization.py", line 230, in _open_file_like
return _open_file(name_or_buffer, mode)
File "/home/jp/miniconda3/envs/torch/lib/python3.8/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: ''
made up check point. (file doesn't exist) (torch) ➜ One-Shot_Free-View_Neural_Talking_Head_Synthesis git:(main) ✗ python demo.py --config config/vox-256.yaml --checkpoint ./check.pt --source_image '/home/jp/Desktop/2.jpg' --driving_video '/home/jp/Documents/gitWorkspace/SimSwap/J11-wm.mp4' --relative --adapt_scale --find_best_frame
demo.py:28: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
config = yaml.load(f)
Traceback (most recent call last):
File "demo.py", line 282, in
generator, kp_detector, he_estimator = load_checkpoints(config_path=opt.config, checkpoint_path=opt.checkpoint, cpu=opt.cpu)
File "demo.py", line 48, in load_checkpoints
checkpoint = torch.load(checkpoint_path)
File "/home/jp/miniconda3/envs/torch/lib/python3.8/site-packages/torch/serialization.py", line 579, in load
with _open_file_like(f, 'rb') as opened_file:
File "/home/jp/miniconda3/envs/torch/lib/python3.8/site-packages/torch/serialization.py", line 230, in _open_file_like
return _open_file(name_or_buffer, mode)
File "/home/jp/miniconda3/envs/torch/lib/python3.8/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: './check.pt'
— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.
Hello, ZLH Thank you for you great implementation.
Would you mind providing the pretrained models (checkpoints)? Thank you for your help.
Jihye 😊