BasicSR

BasicSR copied to clipboard

Can you provide the trainning code of DFDNet?

Nise-2-meet-U

 thanks for your job. May I ask which model is used for video/image denoise and can these models be transformed to Caffe/ONNX/Tensorflow-Lite?

xsy123xsy

can you tell me where is sft_arch.py? THANK YOU

wyuzyf

I am thinking using sum will let the loss magnitude change if we change the batch size or input resolution. Is there any reason to use 'sum' instead of 'mean'?...

hcwang95

Hi, EDVR is a amazing model, but its compution effort is large. Could we use some tech like group convolution to reduce the FLOPS? As https://github.com/DestinyK/MobileSR shows it use "parallel...

leiwen83

I get unsatisfying results when reproducing your results!

5

I got unsatisfying results when trying to reproduce your results! The following is what I did: I used the matlab downsample kernel, and I only used the DIV2K as the...

hellohawaii

Hi, xinntao. I implemented your training code with DF2K dataset and I get the corresponding result: x4 | Set5 | Set14 | Urban100 | BSD100 | Manga109 Baseline | 32.61/0.9003...

ZuoYuShen

Thanks for your wonderful job! I want to visualize the feature maps of the interlayers in the network, can you give me some help. I think this part of the...

gaoxiangv1

Thanks for your amazing work. IF POSSIBLE, I am going to implement image super resolution app via android studio by using your repo . I wanna know that if this...

ddtran30

How to train the pretrain models?

1

Hello: I want to retrain the PSNR pretrain models for ESRGAN,what i should do?

qwerdf4