Johnson yue

WGAN-GP for Training MSG_ProGAN is failed

3

Hi, I read your newest version paper (v3) in arxiv, and i saw that add MSG_styleGAN information, I'm glad to see it , but I have some question about paper...

https://github.com/akanimax/BMSG-GAN/blob/d06316974d1d84bd2077f8c558ebaf9d967205df/sourcecode/MSG_GAN/CustomLayers.py#L342 I think input feature x , the shape of **x** is (BS, C, H, W) and the shape of **y** is (BS, 1, H, W) so the output of...

rt。Do you plan to implement with pytorch？？ Or someone want to try？？

Thank you very much for sharing you code . But when I test, the inferece time for lenet or pvanet didn`t speed up. But accuracy is very lost.

Update discriminator.py

1

More general for any image size

remove redundant code for class_to_idx

This is a bug and 'ResNet' object has no attribute 'module'

1

https://github.com/yhenon/pytorch-retinanet/blob/a76e56eb537be476abc914587ae92ab542e2b3e4/train.py#L110 Can you provide a finetune code ??

How to Save Model and Save CheckPoint in tf.keras mode

1

Hi, your tutorial is very helpful to me!!! Thank you very much. I read your code many times， and I found it is not include __How to Save Model__, as...

### 📚 The doc issue How to run colossal AI in background？？ I was link the remote GPU ， when I used `nohup colossalai run --nproc_per_node 1 colossai_train.py --config configs/colossai/config.py...

I watch you code and see you code using othernetworks.py inpaintG, not using ResnetGenerator I want to know is Inpaint G better than ResnetG??