Issues
- 13
how to use syncnet_python and training steps
#124 opened by 1129571 - 9
train_syncnet_sam.py加载无反应
#110 opened by fzuqxt - 0
- 1
why train_syncnet_sam.py set img_size=384?
#157 opened by qingshuiyuyu - 1
- 0
how to prepare training dataset
#156 opened by dxLu - 1
大家有遇到过执行train_syncnet_sam.py后出现的张量维度不一致问题吗:tensor a (1024) must match the size of tensor b (9216),如图
#155 opened by yuanmaitian - 0
出售一份自己人工手动下载人脸数字人的数据集原始视频 ,视频分辨率1080-4k口播视频,可用于训练wav2lip-192,wav2lip-288,wav2lip-384,wav2lip-512,DINet-256,NeRF等模型。微信douzijun1999 请注明来意
#154 opened by dousang1999 - 0
每次训练停止,都从头开始,怎么修改能继续上次断开的地方开始
#153 opened by zn123 - 3
also around the 0.69 on 240000 steps
#118 opened by cncbec - 0
- 6
Model copying reference frames as it is
#122 opened by mudassirkhan19 - 4
Why can’t training start?
#142 opened by piwawa - 22
Syncnet loss does not converge
#146 opened by kavita-gsphk - 0
structure and arrangement of dataset before executing any scrip with flow of script execution!!!!!!
#151 opened by vpssa - 2
- 1
DINet
#148 opened by duyquang099 - 0
这个和普通的easyw字幕交换网站lip有什么区别
#149 opened by tuantra-dh - 1
DINet implementation
#136 opened by ozzieakg - 1
wav2lip sam
#128 opened - 6
Training failed. The lip shape of a character cannot change according to changes in speech
#145 opened by Liming-belief - 3
- 4
Why my train loss after introducing sync loss?
#140 opened by Marskly - 6
How to train
#141 opened by see2run - 2
Generated bottom half face always blur.
#144 opened by wangjio - 0
do inference
#143 opened by see2run - 0
Hi sir, I am a beginner and I would like to inquire whether I should prepare a video of no less than 288 or a video of 384
#132 opened by SakuraMaiii - 1
- 4
- 1
train_syncnet_sam.py is not using GPU (RTX 4090)
#138 opened by meng-x - 7
LOSS stuck arount 0.69
#114 opened by ashishjamarkattel - 3
When I use hq_wav2lip_sam_train.py。
#135 opened by yuan7245 - 4
Syncnet training? Chilcken and egg?
#119 opened by sylyt62 - 1
High resolution dataset
#131 opened by akshatgarg99 - 0
video clips length
#137 opened by hnsywangxin - 1
the input of lpips loss
#130 opened by taozhiqi - 2
Hi Brother
#129 opened by langzizhixin - 1
Wav2Lip_SAM freeze_audio_encoder
#127 opened by taozhiqi - 0
Should this be `Wav2Lip_SAM` or `Wav2Lip_384`?
#126 opened by albyho - 5
老哥,你为嘛把项目名称改来改去?
#123 opened by prometheus-alien - 3
Missing License
#125 opened by ntakouris - 3
train_syncnet history,waiting the result
#108 opened by zhangziliang04 - 0
- 0
Is 288 Sam supported? I changed the image size of syncnet to 288 and trained it, but found that the second step does not support 288
#120 opened by einsqing - 0
Help to test the data from open-sourced dataset
#117 opened by Nyquist0 - 0
instruction
#116 opened by Citramones - 1
- 0
- 0
inference no working
#113 opened by dezei547 - 0
Is there a pre-trained model?
#111 opened by 397688551