gangxu822

Traceback (most recent call last): File "build_estimator.py", line 398, in main(args_) File "build_estimator.py", line 358, in main env = Simulator() File "/dockerdata/danielgxu/sucai_paoma/drl-rec-master/simulator.py", line 15, in __init__ self.init_state = self.reset() File...

Hello, please ask: the actual effect is inconsistent with the effect given by the paper. Is this a hyperparameter that needs to be adjusted？

5


Do I have to retrain stage1, stage2, stage3 for new object here? What should i do if want to replace it with my own input data


如题

No module named 'mmcv._ext' 怎么解决

2

from mmpose.models.builder import build_pose_estimator File "/opt/nas/p/conda/envs/MuseTalk/lib/python3.10/site-packages/mmpose/models/__init__.py", line 8, in from .heads import * # noqa File "/opt/nas/p/conda/envs/MuseTalk/lib/python3.10/site-packages/mmpose/models/heads/__init__.py", line 11, in from .transformer_heads import EDPoseHead File "/opt/nas/p/conda/envs/MuseTalk/lib/python3.10/site-packages/mmpose/models/heads/transformer_heads/__init__.py", line 2, in from...

hello，我是用gradio生成对嘴视频的，怎么感觉出来的效果嘴巴都有点抖。有人遇到类似情况吗？求助！

1

https://github.com/user-attachments/assets/aba60c02-1fdf-40ef-be6a-6aac684f1aa7 https://github.com/user-attachments/assets/6203f482-79bd-4054-a363-583a25997215 https://github.com/user-attachments/assets/e13e8972-6a45-4abf-aa20-f6c74e372705 https://github.com/user-attachments/assets/e1b6d542-9753-45de-b6d5-6b1833b9c5ca https://github.com/user-attachments/assets/c24f2939-5eee-489c-95dd-8eec311515af

了不起的工作！请教一些问题

1

我看GPSDiffusion SGDiffusion的输入都是256*256，假如真实图片是3000*4000的分辨率，再resize 到256*256，图片的背景细节会丢失，影子里面的东西也很不清晰，要过超分才可用。这个问题怎么解决