IP_LAP

IP_LAP copied to clipboard

MtYCNN

期待支持288x288或者384x384

1

tailangjun

Ignore frames where face is not detected

1

Hello, great work on this project! is there some way to ignore the frames where faces weren't detected?

musakhawaja

I see the pre-generated crops of faces from individual frames are currently resized to N x N. Will aligning the faces in the same video clip using the facial landmarks...

subharya83

作者您好，请问推理出来的视频为什么分辨率变得很低了，很模糊

fzuqxt

INFO: Created TensorFlow Lite XNNPACK delegate for CPU.

5

how can i fix it

komilaria

how to solve this issue

komilaria

video renderer speed is slow

2

Thank you for your open source. I tried the CUDA_VISIBLE_DEVICES=0 python inference_single.py and got the result ./test_result/129result_N_25_Nl_15.mp4 every thing goes fine, except the inference speed is slow(only got around 5.0it/s...

huangxin168

train video render

2

你好，我想训练一个只适用于某特定人物的模型，请问训练video render时数据集的时长以及多样性是否有要求？

ZJ-CAI

The face cannot be detected when I infer my own input video.

2

Thank for your great work! But when I run the inference_single.py using my own video, the code cannot work. It show: `Traceback (most recent call last): File "inference_single.py", line 509,...

AndrewDing616