Ken1256 issues

Results 14 issues of


                                            Ken1256

Nan loss in RCAN model

https://github.com/wayne391/Image-Super-Resolution/blob/master/src/models/RCAN.py Just change `optimizer = torch.optim.Adam(model.parameters(), lr=1e-4, amsgrad=False)` to `optimizer = adabound.AdaBound(model.parameters(), lr=1e-4, final_lr=0.1)` Nan loss in RCAN model, but Adam work fine.

enc_blk_nums middle_blk_num dec_blk_nums

Different tasks need required different settings?

How to Converting pre-trained pytorch model to MXNet?

Platform (like ubuntu 16.04/win10):win10 Python version:3.6.6 x64 Source framework with version (like Tensorflow 1.4.1 with GPU):torch-0.4.1-cp36-cp36m-win_amd64 (CUDA 9.2) Destination framework with version (like CNTK 2.3 with GPU):mxnet-cu92 --pre(1.3.1b20180927) Pre-trained model...

Dataset link dead

https://competitions.codalab.org/competitions/22220#participate https://data.vision.ee.ethz.ch/alugmayr/NTIRE2019/public/Corrupted-tr-x.zip https://data.vision.ee.ethz.ch/alugmayr/NTIRE2019/public/Corrupted-tr-y.zip https://data.vision.ee.ethz.ch/alugmayr/NTIRE2019/public/Corrupted-va-x.zip https://data.vision.ee.ethz.ch/alugmayr/NTIRE2019/public/Corrupted-te-x.zip https://data.vision.ee.ethz.ch/alugmayr/NTIRE2019/public/DPEDiphone-tr-x.zip https://data.vision.ee.ethz.ch/alugmayr/NTIRE2019/public/DPEDiphone-tr-y.zip https://data.vision.ee.ethz.ch/alugmayr/NTIRE2019/public/DPEDiphone-va.zip https://data.vision.ee.ethz.ch/alugmayr/NTIRE2019/public/DPEDiphone-crop-te-x.zip Can someone re-upload?

SCUNetG need pretrain?

SCUNetG is based on SCUNet checkpoint? thanks

Can only Deblurring/shape with out Upscaling?

Q1: Only train _DeblurringMoudle and return deblur_out is right or need modify some code? Q2: Is possible improve image sharpness, anti-aliasing, Denoising and recovery details? THX

NTIRE 2020 Real World Super-Resolution dataset link dead

Cannot convert to TensorRT.

https://github.com/NVIDIA-AI-IOT/torch2trt/issues/807 TensorRT not support move batch dim. https://forums.developer.nvidia.com/t/tensorrt-does-not-support-permute-in-n-batch-dimension/69925

MPC-BE x64 when to vs.RGBS freeze

``` from vapoursynth import core import vapoursynth as vs pp = VpsFilterSource matrix = "709" pp = core.resize.Spline36(pp, format=vs.RGBS, matrix_in_s=matrix) pp = core.resize.Spline36(pp, format=vs.YUV444P16, matrix=matrix, matrix_in=matrix, range=1) pp.set_output() ``` if...

bug

Can Best-Buddy Loss train without GAN and perceptual loss?

Will it better than L1 loss? Thanks