Yuchuan Tian

Thank you very much for raising this question. Let me check... My basic intuition doing this is that I found ImageNet accuracy would fluctuate by around 0.1% at the last...

I checked the experiments as follows: CIFAR-10 VGG19 experiments are correct at all sparsities; CIFAR-10 ResNet32 experiments are problematic at sparsity 99.5% and 99.9%; ImageNet ResNet-50 experiments are correct at...

Hi Acasia, Sorry for replying late! Here are some updates after thorough checking: 1. The codes have been updated. A patch is added to resolve the problem. 2. The latest...

It's not your fault; rather, the GPU Memory is too small for IPG. You can change to GPUs with a larger memory (like V100 with 32G memory), or you may...

你好，感谢对我们工作的关注！ 将eval_folder参数递入exec.py时，会只运行validation，不运行训练。

Thanks for your interest in our work! Actually, the official dataset you have downloaded does not include any LR image. You will have to preprocess it according to the matlab...

The preprocessed dataset could be downloaded from this link: https://huggingface.co/datasets/yuchuantian/BasicSR_SR_test

Actually, ipg_kit refers to the script ipg_kit.py The command must be run at the folder "IPG" (i.e. ipg_kit.py must be in the root directory) in order to let the code...

As for the test dataset: previously I downloaded them from somewhere but they are protected within internal devices. I have provided a way to replicate the testsets based on the...

I also have a tedious solution to "no module named ipg_kit" (But it always works!!!) Copy everything in ipg_kit.py to LowLevel/IPG/basicsr/archs/IPG_arch.py, and remove the dependency of IPG_arch.py on ipg_kit. I...