Jiu XU

@RyanCV It looks like a gpu problem, please put CUDA_VISIBLE_DEVICES=($Your_available_gpu_device_index) before python test.py and have a try.

@chenyuntc Thanks, I also fixed the weights for top layers, but the result didn't improve. As you mentioned, it might be the reason of BN and biases. I'll have another...

Hi @chenyuntc, I've trained the model with: 1. Fix the first block. 2. Learning rate for biases is not doubled. 3. All batch normalization parameters are fixed. 4. Use 1e-4...

Hi, @susuml for training LapSRN x8, you will need to modify the https://github.com/twtygqyy/pytorch-LapSRN/blob/master/data/generate_train_lap_pry.m and generate h5 which contains x2 x4, and x8 images. After that, just simply change the network...

Hi @sriprabhar you can use the skimage for SSIM calculation, the two inputs should be in grey scale and in uint8 format. (You can check this [article](https://www.pyimagesearch.com/2014/09/15/python-compare-two-images/) for more details)

Hi @sriprabhar, how much difference did you get from the model you trained and the performance on the paper? Did you try to reproduce the result in my repo?

Hi @sriprabhar thanks for the update. 0.3 dB PSNR improvement looks promising, good job. For the SSIM, I guess there is still some different from Matlab implementation with the one...

@yuanshuai220 @CasdDesnDR Please refer https://github.com/twtygqyy/pytorch-SRResNet/blob/master/data/generate_train_srresnet.m for adding flipping and rotation

Hi @baiyancheng20, I followed the LapSRN paper for the implementation. Actually, you can check https://github.com/twtygqyy/pytorch-SRResNet which I used RGB image as inputs.

@sriprabhar Hi, I understand that you tried to overfit the network on a small dataset. How is the loss looks like in your training? Did it converge well?