XLSR icon indicating copy to clipboard operation
XLSR copied to clipboard

PyTorch implementation of paper "Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devices"

Results 6 XLSR issues
Sort by recently updated
recently updated
newest added

你好,我用这个模型在非bilinear退化数据集上表现不理想,PSNR只有23左右

![image](https://github.com/cxzhou95/XLSR/assets/66729924/c08b6eed-7989-4df3-8019-2f61105e5201)

While loading the regular `best.pt` model works, but loading the quantized models (like `QAT_quantized_model.pt`) throws an error. What is the problem? `python test.py --model exp/OneCyclicLR/QAT_quantized_model.pt --device cpu` Error: ``` C:\Users\AppData\Local\anaconda3\Lib\site-packages\torch\serialization.py:995:...

When I try to run `test.py` using defaults values (with the correct model path), it gives the following error. What is the problem? ``` Traceback (most recent call last): File...

![image](https://user-images.githubusercontent.com/24247356/188560737-42692049-3261-425a-a51d-d3ebc5c0e4d2.png)

Hi!Thanks for ur work. I wanna know that how u guys to test the benchmark dataset since the pics' sizes(which are constructed by x3 downsapmled pics) are not equal to...