-
I wanna train/finetune over my own dataset, but I didn't find the training code:)
-
instead on only PSNR what about
[MS-SSIM](https://en.wikipedia.org/wiki/Structural_similarity#Multi-Scale_SSIM)[¹](https://ece.uwaterloo.ca/~z70wang/publications/msssim.html)[²](http://sse.tongji.ed…
-
As the title says, image magick's compare only uses PSNR, mse, ae, rsme and that's it. Since you support ssim(which should be the default as it's based upon how the human eye sees things compared to p…
-
Hi, how to choose the loss type?
-
作者您好
这段时间在尝试复现您的实验时发现直接MS_LAP/test_cuda.ipynb这个demo无法复现您的结果，阅读代码后发现您在MFF2.py文件中259行处优化目标应该是写反了，修改为(1-ssim_out).backward()之后可以复现您的结果
-
The page takes several seconds to show up currently. Can be 5..7 seconds, PageSpeed measures e.g. 5.3s to Largest Contentful Paint on Desktop:
https://pagespeed.web.dev/analysis/https-w-m-github-io…
-
Hello, thanks for the sharing the code used in your paper. I am try to run the experiments on my own server to obtain each decoded image, but I am facing some issues when using MAML weights on Kodak. …
-
Hello,If possible, could you provide us the points of GAACNN(the value of x and y axis) on the RD-Curve Figure 5 on the paper?(Rate-distortion performance evaluation of image compression methods on th…
-
Hello, when attempting to run "python train_generic.py --model MARNet --epochs 100 --dataset qnrf --train_json json/qnrf_train.json --val_json json/qnrf_val.json --loss 3avg-ms-ssim --lazy_val 0" I ge…
-
It's likely we'll be testing new compressors at some point; would be nice to run and test these with MS-SSIM and also timing vs some baseline without having to drive them through AME etc.
For any c…