New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
优化推理效果的讨论 #107
Comments
|
|
|
You can set the crop-radius Crop_radius_example1.mp4 |
我改用 min_crop_radius后确实好一些了,非常感谢。另外问一下,预处理的时候用到 compute_crop_radius的地方是不是也得修改 Celebrity_._facial_dubbing_add_audio.mp4 |
发现推理出来的脸部比原脸要胖一些,高度要短一些,不知道是啥原因导致的。这应该也是代码中要用 random_scale = 1.0的效果 random_scale = 1.05的效果 random_scale = 1.1的效果 random_scale = 1.15的效果 |
你是按照源代码的训练方式训的吗? 源代码训练太慢 |
差不多,但是预处理代码做了一些修改 |
thanks for comparison I have removed randomness in my repo LipSick and set this to 1.1 hopefully that works well, I had to stop using random as the crop radius results i print kept changing and I needed consistency |
嗯,我觉得单纯修改 random_scale还不能完全消除原来的下巴,特别是在脸部边缘有阴影的情况下,我在尝试加一些图像处理的逻辑以实现彻底消除 |
did you reproduced syncnet? |
可以用推理的视频先做下finetune,应该会好一些 |
可以试试landmark结合光流法平滑处理,我在nerf类的项目里见到过这样的做法。 |
You are right it won't fix the chin, an experiment you can try since you are using open-face csv is track the face, then in a video editor move the person in the video slightly higher or slower so the video is still 1920x1080 but now you have a black bar either below or on top. |
请问是 GeneFace++还是 ER-Nerf等 |
synctalk |
收到,非常感谢,是不是那个 vis_parsing_maps函数呀,我学习一下 |
嗯,finetune肯定是可以的,我在想有没有更省事的方法 |
是的,要支持中文的话得自己训练 syncnet |
你好,请问openface是在Linux上使用的吗?需要用哪些命令选项啊?还有个问题,那个 min_crop_radius 是在哪个地方修改的呢?感谢 |
Linux上可以使用 FeatureExtraction,具体参数可以到官网查 |
这个不就是改 |
data_processing.py中也有调用 compute_crop_radius的,我觉得比较好的改法是将 random_scale的默认值直接写在定义中,外面默认就不用填 random_scale了 |
通过几个月的训练,踩过不少坑,终于把整个流程都走通了,下面是中文推理效果
Celebrity_._facial_dubbing_add_audio.mp4
目前还存在几个大问题,这里做一下总结
The text was updated successfully, but these errors were encountered: