Issues
- 1
Cannot install on python3.10
#125 opened by sumitmamoria - 0
Is there a 128 Clip training model?
#124 opened by giandre - 2
关于visual quality的计算方式
#110 opened by aidenyzhang - 0
Evaluation
#123 opened by thd-ux - 5
frame 256的模型同步性很差
#122 opened by liwang0621 - 9
frame阶段训练loss出现倒刺现象
#116 opened by liwang0621 - 38
优化推理效果的讨论
#107 opened by tailangjun - 20
改用chinese-hubert-large来生成音频特征
#95 opened by tailangjun - 4
训练时出现奔溃帧,不知原因?
#113 opened by flysky126 - 8
有大佬成功训练出效果较好的 syncnet吗?
#105 opened by tailangjun - 2
clip阶段sync loss的问题
#118 opened by liwang0621 - 0
num_workers 设为非 0 后报错
#121 opened by sunjian2015 - 0
关于训练过程中的验证
#120 opened by sunjian2015 - 1
AI Dubbing API (with multi-speaker lipsync)
#119 opened by mvoodarla - 2
I need a convergence chart for training
#117 opened by Inferencer - 1
- 1
Tensorflow version 1.xx is PAIN (COLAB)
#115 opened by sahilg06 - 14
Who needs high-quality lip sync - contact me!
#109 opened by Chechgroup - 2
可不可以不使用 openface?
#112 opened by sunjian2015 - 1
🤢 New repo LipSick 🤢🤮
#104 opened by Inferencer - 0
求助,clip训练后,推理出来的视频会出现花屏帧?
#108 opened by flysky126 - 0
Model is changing Skin Tone
#106 opened by kalpesh-maru - 1
How to deploy the model to replicate.com
#84 opened by kiostudio - 2
- 2
讨论一下 DINet微调的问题
#102 opened by tailangjun - 6
Error while frame training
#91 opened by ashu-jb - 4
话说 syncnet_64mouth.pth和 syncnet_128mouth.pth有啥作用吗
#101 opened by tailangjun - 1
NVIDIA GeForce RTX 3090 with CUDA capability sm_86 is not compatible with the current PyTorch installation
#100 opened by ttkrpink - 0
- 1
请问DeepSpeech这个模型output_graph.pb是怎么生成的?
#94 opened by wzy522 - 1
- 1
hdtf dataset preprocess
#97 opened by shanzhajuan - 1
Pre-trained model error
#78 opened by NickVitali - 1
File "data_processing.py", line 90, in crop_face_according_openfaceLM raise ('run last step to extract video frame')
#96 opened by obtuseanglor - 0
Possible error of parallel training
#93 opened by YinzhenWang - 9
Tips for train syncnet
#73 opened by KimGyeongsu - 0
- 14
I did an experiment and did not get very good precision ( the face KEPT TALKING when there was a SILENCE)
#87 opened by AIhasArrived - 11
- 0
(持续学习——数据增量)continuous learning
#88 opened by 1129571 - 8
Error- "Our method cannot handle videos with large change of facial size!!"
#82 opened by GayatriVadaparty - 0
Could rtx4070 12g be enough for training?
#86 opened by kevinzc9 - 0
If i new sample, for which dinet pretrained model is not working. I want to fine tunning new sample. how would one do it ?
#85 opened by JoraAlgorithm - 1
我们创建了一个中文讨论组,有需要的加我微信douzijun1999
#83 opened by dousang1999 - 2
请问trans_conv网络中用了11和7的卷积核是做什么考虑
#75 opened by nopeiyu - 6
My own data, the effect is very poor, come with a mask, this is why
#77 opened by zhanghongyong123456 - 2
- 6
Openface problem "detected landmarks"
#80 opened by NickVitali - 3
File "inference.py", line 59, in <module> raise ('video frames are misaligned with detected l
#76 opened by itzsalle - 0
Loss convergence损失收敛问题
#74 opened by 1129571