BasicSR

BasicSR copied to clipboard

Suggestion: LPIPS

3

Hi, thanks a lot for your meaningful work. Maybe you could add the LPIPS to the evaluation script at your convenience.

liqilei

Test on sub-image instead of whole image

2

Hi! @xinntao I find that, when testing, the PSNR and visual results are based on the cropped image (i.e, 480x480 sub-image) instead of the whole image. However, in my experience,...

yjsunnn

Error in testing EDVR

2

error in modulated_deformable_im2col_cuda:invalid device function

XIAJIUFAN

On the problem of stagnation of training ESRGAN generator

4


zkh123456789

Error when training basicvsr x2 model after 300k iterations

4

I modified the basicvsr_arch.py to train the x2 model. It worked fine when I trained for the first 300k iterations. After 300k iterations, there is an error. I tried to...

Bouby308

out of memory on testing

2

I set the batch size to 4 during training and it works fine. However, when I tried to test, it resulted in "out of memory" CUDA errors. And I can't...

joneschunghk

ONNX seems to be the defacto deployment option and scripts are available for training and deployment of BasicSR weights to an onnx version of the model; but for accelerating past...

Sazoji

Unable to predict on single channel images

1

I was able to train the PSNR model for single channel image but it breaks in the prediction part. Any clue? I'm passing `in_channel` and `out_channel` as 1 in the...

purijs

Results in MSU Video Super Resolution Benchmark

1

Hello, [MSU Graphics & Media Lab Video Group](https://videoprocessing.ai/) has recently launched Video Super Resolution Benchmark. We provide a comprehensive comparison of a variety of different VSR models. You can see...

Kirillova-Anastasia

Hello, Thank you for providing good papers and code. I'd like to ask a question about the ESRGAN pre-trained model. I wonder how the pre-trained model parameters provided on your...

hayeong0