AttributeError: module 'face_detection' has no attribute 'FaceAlignment'

[wxc1207]

I am trying to sequentially switch the versions of face-detection to (0.1.1, 0.1.2, 0.1.3, 0.1.4, 0.2.0, 0.2.1, 0.2.2), but I still cannot find the face-detection module. Is this because of version incompatibility, or is there another issue? I hope to get help：：

(wav2lip1) root@autodl-container-b52c468700-adae5615:~/autodl-fs/wav2lip# python inference.py --checkpoint_path /root/autodl-fs/wav2lip/checkpoint_path/wav2lip.pth --face /root/autodl-fs/wav2lip/wxc-data/origin.mp4 --audio /root/autodl-fs/wav2lip/wxc-data/123.wav Using cuda for inference. Reading video frames... Number of frames available for inference: 8325 (80, 2627) Length of mel chunks: 981 0%| | 0/8 [00:00<?, ?it/s] Traceback (most recent call last): File "inference.py", line 280, in main() File "inference.py", line 250, in main total=int(np.ceil(float(len(mel_chunks))/batch_size)))): File "/root/miniconda3/envs/wav2lip1/lib/python3.6/site-packages/tqdm/std.py", line 1127, in iter for obj in iterable: File "inference.py", line 113, in datagen face_det_results = face_detect(frames) # BGR2RGB for CNN face detection File "inference.py", line 69, in face_detect detector = face_detection.FaceAlignment(face_detection.LandmarksType._2D, AttributeError: module 'face_detection' has no attribute 'FaceAlignment'

[hello9527-z]

你需要手动下载face_detection，然后放在与inference.py同一文件夹下

[IoannisDem]

I believe you try to pip install face-detection from here: https://pypi.org/project/face-detection/

However, the face_detection model is defined within this repo which is taken from here: https://github.com/1adrianb/face-alignment (Here is the relevant folder from this repo: https://github.com/Rudrabha/Wav2Lip/tree/master/face_detection)

Basically, you try to imoprt the wrong model