KAIR

KAIR copied to clipboard

main_test_rrdb.py

3

用main_train_rrdb_psnr.py训练出model之后，用test代码不能正常超分图片。 用原model = net(in_nc=3, out_nc=3, nc=64, nb=23, gc=32, upscale=4, act_mode='L', upsample_mode='upconv') 得出的输出会变黄色，后面按照option改成了 model = net(in_nc=3, out_nc=3, nc=64, nb=23, gc=32, upscale=4, act_mode='R', upsample_mode='upconv') 得出的输出会变黑色 训练过程中的验证是能正常超分出来的

House-Leo

请问代码里面没有训练过程可视化的代码吗 例如 使用tensorboard， 直接保存在 train.log 中 似乎不是很能直观感受

tongchangD

请问bsrgan中，isp_model应该怎么设置？

3

这部分相关的设置和信息似乎没有，有什么好的预训练模型可以参考吗 谢谢

riverlight

Hi, thanks for this great work! I have some questions regarding DnCNN model training. In the paper, the loss function applied is MSE Loss, may I know why it is...

yx-chan131

How can I train USRGan and other tiny models?

3

Hey, thanks for contributing. Your work is awesome. I tried to find the USRGan and USR-tiny models training support, but didn't get any of these? Is there any support for...

coreqode

Would be nice to have a working image on the docker hub.

MariasStory

Hi, do you have the data preperation code and training code for the DnCNN3 model that can handle SISR noise, blocking artifacts and gaussian noise?

supriyaarun27

I want to train the FFDNET model from the scratch for gray scale Images in Pytorch framework without using the pre-trained models available at https://drive.google.com/drive/folders/13kfr3qny7S2xwG9h7v95F5mkWs0OmU0D After putting the dataset in...

muhammad-aamir94

Excessive memory usage usrnet

1

I'm testing usrgan and I'm surprised that I'm not able to apply it to a 750x1000 px image, considering that the model has only 17016016 parameters. The error is `CUDA...

jofuelo

Difference of almost 5dB when training with opencv/pillow bicubic.

1

Hello again, There is a difference of almost 5dB when I train with opencv/pillow bicubic kernel as compared to default matlab. Is matlab kernel easy to learn, as compare to...

coreqode