Oli_Zhan

> I am ready my own wav file and sequential obj mesh datasets(5023x3). voca training session used datasets as .npy and .pkl file and I want to know about how...

> > Can you please give more details, why you cannot download the pre-trained model? > > Thanks. > > I didn't make any changes of the source code except...

I switch the tensorflow to cpu version, it still doesn't work. :( 🆘

same error QAQ

It's a bit late but can be fixed by installing an older version of Imageio `pip install imageio==2.6.1 `

> in tf_mesh_render/WORKPLACE, change pkg to this: ``` http_archive( name = "com_google_googletest", urls = ["https://github.com.cnpmjs.org/google/googletest/archive/609281088cfefc76f9d0ce82e1ff6c30cc3591e5.zip"], strip_prefix = "googletest-609281088cfefc76f9d0ce82e1ff6c30cc3591e5", ) ```

> Sorry. I am clearly missed something. Can you clarify please. > > What I am must do for getting result video where man from "cnn.mp4" video speak with voice...

have u solved this problem? facing the same problem QAQ

臣附议

> > Why don't you use it? Is the performance not good?！ @guoqincode > > I used it. Have you do comparison experiments? Is training temporal module from scratch much...