using expression center
Load checkpoint from: checkpoints/DNet.pt
Load checkpoint from: checkpoints/LNet.pth
Load checkpoint from: checkpoints/ENet.pth
[Step 3] Using saved stabilized video.
[Step 4] Load audio; Length of mel chunks: 523
[Step 5] Reference Enhancement: 100%|███| 464/464 [01:20<00:00, 5.77it/s]
[Step 6] Lip Synthesis:: 0%| | 0/33 [00:00<?, ?it/s]No face detected in this image███████▍ | 381/464 [00:21<00:02, 35.72it/s]
No face detected in this image
landmark Det:: 100%|████████████████████| 464/464 [00:23<00:00, 19.67it/s]
100%|████████████████████████████████| 464/464 [00:00<00:00, 35074.11it/s]
100%|██████████████████████████████████| 464/464 [00:00<00:00, 785.98it/s]
FaceDet:: 100%|█████████████████████████| 116/116 [01:43<00:00, 1.12it/s]
[Step 6] Lip Synthesis:: 0%| | 0/33 [02:09<?, ?it/s]
Traceback (most recent call last):
File "inference.py", line 355, in
main()
File "inference.py", line 224, in main
for i, (img_batch, mel_batch, frames, coords, img_original, f_frames) in enumerate(tqdm(gen, desc='[Step 6] Lip Synthesis:', total=int(np.ceil(float(len(mel_chunks)) / args.LNet_batch_size)))):
File "D:\Anaconda\envs\lipsync\lib\site-packages\tqdm\std.py", line 1182, in iter
for obj in iterable:
File "inference.py", line 305, in datagen
face_det_results = face_detect(full_frames, args, jaw_correction=True)
File "D:\lipsync\video-retalking\utils\inference_utils.py", line 133, in face_detect
raise ValueError('Face not detected! Ensure the video contains a face in all the frames.')
ValueError: Face not detected! Ensure the video contains a face in all the frames.
Press any key to continue . . .
using expression center Load checkpoint from: checkpoints/DNet.pt Load checkpoint from: checkpoints/LNet.pth Load checkpoint from: checkpoints/ENet.pth [Step 3] Using saved stabilized video. [Step 4] Load audio; Length of mel chunks: 523 [Step 5] Reference Enhancement: 100%|███| 464/464 [01:20<00:00, 5.77it/s] [Step 6] Lip Synthesis:: 0%| | 0/33 [00:00<?, ?it/s]No face detected in this image███████▍ | 381/464 [00:21<00:02, 35.72it/s] No face detected in this image landmark Det:: 100%|████████████████████| 464/464 [00:23<00:00, 19.67it/s] 100%|████████████████████████████████| 464/464 [00:00<00:00, 35074.11it/s] 100%|██████████████████████████████████| 464/464 [00:00<00:00, 785.98it/s] FaceDet:: 100%|█████████████████████████| 116/116 [01:43<00:00, 1.12it/s] [Step 6] Lip Synthesis:: 0%| | 0/33 [02:09<?, ?it/s] Traceback (most recent call last): File "inference.py", line 355, in
main()
File "inference.py", line 224, in main
for i, (img_batch, mel_batch, frames, coords, img_original, f_frames) in enumerate(tqdm(gen, desc='[Step 6] Lip Synthesis:', total=int(np.ceil(float(len(mel_chunks)) / args.LNet_batch_size)))):
File "D:\Anaconda\envs\lipsync\lib\site-packages\tqdm\std.py", line 1182, in iter
for obj in iterable:
File "inference.py", line 305, in datagen
face_det_results = face_detect(full_frames, args, jaw_correction=True)
File "D:\lipsync\video-retalking\utils\inference_utils.py", line 133, in face_detect
raise ValueError('Face not detected! Ensure the video contains a face in all the frames.')
ValueError: Face not detected! Ensure the video contains a face in all the frames.
Press any key to continue . . .