Xinyu Gong

Thanks for your great effort! Do you have any plan in implementing Inception score in pytorch?

In test.py, it seems that you have made a careless mistake: `pred = _predictFromArrays_(model, images[left], images[1], images[2], bs)`, while the function only has 4 arguments. `def _predictFromArrays_(model, left, right, bs)`

The compatibility for the later version pytorch

1

In the original implementation, an error will occur "RuntimeError: A view was created in no_grad mode and is being modified inplace with grad mode enabled" using PyTorch 1.8.

### ⚠️ Search for existing issues first ⚠️ - [X] I have searched the existing issues, and there is no existing issue for my problem ### Which Operating System are...

Hi, thx for your great code! However, when I run train.py, I've got `Check failed: CUDA_SUCCESS == dynload::cuCtxSetCurrent(cuda_context->context()) (0 vs. 4)` Could you help me?

### Is there an existing issue for this? - [X] I have searched the existing issues and checked the recent builds/commits ### What would your feature do ? Align Your...

### Feature request / 功能建议 Great work! Do you consider to support `system message` in the future? ### Motivation / 动机 N/A ### Your contribution / 您的贡献 N/A