运行inference.py报错，求大神告知怎么解决

guo-huan commented 4 months ago

执行命令：python inference.py --driven_audio D:\SadTalker\examples\driven_audio\chinese_news.wav --source_image D:\SadTalker\examples\source_image\happy.png --enhancer gfpgan

报错： Traceback (most recent call last): File "inference.py", line 158, in main(args) File "inference.py", line 55, in main preprocess_model = CropAndExtract(path_of_lm_croper, path_of_net_recon_model, dir_of_BFM_fitting, device) File "D:\SadTalker\src\utils\preprocess.py", line 46, in init self.kp_extractor = KeypointExtractor(device) File "D:\SadTalker\src\face3d\extract_kp_videos.py", line 16, in init self.detector = face_alignment.FaceAlignment(face_alignment.LandmarksType._2D, device=device) File "D:\anaconda3\envs\SadTalker_ENV\lib\enum.py", line 384, in getattr raise AttributeError(name) from None AttributeError: _2D

guo-huan commented 4 months ago

找到问题了，已解决

nitinmukesh commented 2 months ago

@guo-huan

How did you fixed the issue?

a907066892 commented 2 months ago

没有下载模型到checkpoints文件夹吧

OpenTalker / SadTalker

运行inference.py报错，求大神告知怎么解决 #945