Hao Zhang

Results 8 issues of Hao Zhang

1. Performance can't match the orginal paper (I don't have enough GPUS to train Imagenet. ) 2. It does't support hybrid now because mxnet doesn't have same padding.

I want to use this function in my project. But I find no such function for mat.data in this library.

Here is the code, When Print out the leftimage after convert leftex to mat, it's a white image, and all the pixel values is 205 ` Texture2D lefttex = new...

I want to use it on cpu do real time voice conversion, I don't know whether the model fits my task.

I'm using texture2d example to do real time detection for my VR device, I found it is very slow, any suggestions to improve it ?

It can run in a docker envinment when I use `xvfb-run -s "-ac -screen 0 1280x1024x24" python train.py ` But I get the following error when I use the script...

### System Info I try from transformers.models.t5.modeling_t5 import T5_BiLDModel, but it doesn't work. I build the library from transformer repo. ### Who can help? _No response_ ### Information - [...