-
个人训练x2模型时的PSNR增长缓慢,感觉只在35dB小范围增长,不知道后续增长能否在验证集上达到38dB左右
想参考一下你们训练的epoch 和PSNR之间的关系曲线
-
In the example(/sr/edsr. py) you provided, before converting to INN, the pixel shuffle structure of edsr was replaced with torch. nn.Upsample, meaning that the structure of the INN model and DNN model…
-
-
Finally, I found the code of the RFDB is not the same as the paper.
-
I tried to run
`CUDA_VISIBLE_DEVICES=0 python main.py --model EDSR --scale 2 --save edsr_x2 --n_resblocks 32 --n_feats 256 --res_scale 0.1 --reset --ext sep_reset`
on a single Tesla V100, but the tr…
-
![image](https://user-images.githubusercontent.com/49818346/106976303-ea326c00-6736-11eb-8855-e0c782c73e79.png)
It drops some errors and I can't seem to fix it, if you could tell me what changes sh…
ghost updated
3 years ago
-
Hi, thanks for your work. When I want to reproduce the result using the DIV2K dataset. When calculate the ssim it raises the error
File "/mnt/new_ssd/stefen/code/AdaBM/src/utility.py", line 265, in s…
-
from .contrast_model.unet import build_model as UNET
from .contrast_model.unet_multi import build_model as UNETMULTI
from .contrast_model.mcsr import build_model as MCSR
from .contrast_model.edsr…
-
Hi @colorjam ,
As per the paper, claimed model size is 1.518MB for EDSR, 0.631MB for 8bit EDSR, 0.484MB for 4-bit EDSR model but in you google drive shared models all 3 models are of 6MB size. Can …
-
Thanks for sharing the code.
But unfortunately, the training result from setting in run.sh doesn't meet the results of the paper.
Training for 8bit EDSR x4 only reaches 31.45 for set 5, which is far…