DASR
DASR copied to clipboard
csjliang
Official implementation of the paper 'Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution' in ECCV 2022
Traceback (most recent call last): File "dasr/train.py", line 11, in train_pipeline(root_path) File "/home/chenz/DASR/basicsr/train.py", line 128, in train_pipeline model = build_model(opt) File "/home/chenz/DASR/basicsr/models/__init__.py", line 27, in build_model model = MODEL_REGISTRY.get(opt['model_type'])(opt) File...
Hello How are you? Thanks contributing to this project. I trained a model using 4 GPUs and 5 workers. I did NOT change any parameters except dataset path. I got...
Hello How are you? Thanks for contributing to this project. Did you consider degradation of image by motion blur too?
Traceback (most recent call last): File "dasr/train.py", line 11, in train_pipeline(root_path) File "/home/chenz/DASR/basicsr/train.py", line 155, in train_pipeline train_data = prefetcher.next() File "/home/chenz/DASR/basicsr/data/prefetch_dataloader.py", line 76, in next return next(self.loader) File "/home/chenz/anaconda3/envs/DASR4/lib/python3.7/site-packages/torch/utils/data/dataloader.py",...
 thanks for your work! I can train this work successfully,but when I want to execute the test.py, an error message is reported,can you please tell me how to solve...
In your paper, you mentioned User-Interactive Super-resolution, how can I manually increasing and de-creasing the scale of blur kernel or manually increasing and decreasing the level of noise?
Excellent work，but the idea of meta-learning based degradation adaption has been explored in the following TIP paper. Is it better to add this reference? @article{yin2022conditional, title={Conditional Hyper-Network for Blind Super-Resolution...
Hello, [MSU Graphics & Media Lab Video Group](https://videoprocessing.ai/) has recently launched two new Super-Resolution Benchmarks. * [Video Upscalers Benchmark: Quality Enhancement](https://videoprocessing.ai/benchmarks/video-upscalers.html) determines the best upscaling methods for increasing video resolution...
I have two questions. 1. the sinc kernel_size may be negative when the prob larger than final_sinc_prob? https://github.com/csjliang/DASR/blob/ff2e1ec02c767b75d09b5d60f85c5cbd4115d058/dasr/models/DASR_model.py#L106 2. why are the previous degradation params overwritten , that is to...
