peylnog

Could you please provide the method of reproducing other methods in the paper? This repo Only provide vanilla AE .

Deraining reproduction result seems a little different from report result on paper

2

Because the code using the [torch.backends.cudnn.benchmark=True](https://github.com/swz30/MPRNet/blob/main/Deraining/train.py#L10) , I know it cannot completely repetition. Then , I reproduced it on my 8x2080TI without any code change, and here's result I got....

train datasets

1

Hi,can you provide train datasets you use to achieve VDSR PyTorch result？

hello , i have a question about reproduce ,out_image is strange by your weights, maybe there are something wrong in png. and jpg , could you describe reproduction in detail...

Test Datasets

3

Hello, I can't find your test set. Can you share it ? Thanks a lot

About acc

1

Dear Dr.andrew I'm sorry to bother you. I'm quite interested in following your work after reading your paper, "CNN-generated pictures are surprisingly easy to recognize... for now." But I ran...

Training time

2

When I try to replicate CNNDetection, It looks like training epoch is 10000. It takes a long time to train ! Can I reduce epoch ? And , how much...

looking forward training and testing code！

3

Thanks for your excellent work. looking forward training and testing code！

Thanks for your excellent work！ Can you release complete implementation code based Pytorch？ Previous official Pytorch implementation is uncompleted , and MindSpore version is hard to train on my own...

Training and Test datasets

8

Thank you so much for this excellent work. Can you open source the training set and test datasets used in the paper.