Feng Ruicheng comments

Results 16 comments of


                                            Feng Ruicheng

hi

`Distributed` and `Slurm` training are supported for multi-GPUs training, checkout [TrainTest.md](https://github.com/xinntao/BasicSR/blob/master/docs/TrainTest.md).

Hi, for camera setup, please refer to https://github.com/jnjaby/DISCNet/issues/15#issuecomment-1013645741. I don't quite understand the second question. What do you mean by energy cut-off? Can you make it more specific?

Could you release the code that synth PSF by formula 2?

Hi, we couldn't release the PSF simulation code due to our collaborator's policy.

Test your own data set

Hi, `cv.imread` will return image with data type `uint8`. You need to first convert it into `np.float` and then store as `.NPY` file.

Quantization

@mathmanu I am confused about the procedure of quantization at eval phase. As defined in [/src/caffe/net.cpp](https://github.com/tidsp/caffe-jacinto/blob/ff092f84472c73292bc56f0a01d6bb35769d674c/src/caffe/net.cpp#L676), the dynamic frac-bits are set before forward. Does it mean the quantization ranges of...

Please make a gradio demo that can utilize features proposed in paper thank you so much

Thanks for the suggestion.

Please make a gradio demo that can utilize features proposed in paper thank you so much

Hi all, please check out the demo at https://huggingface.co/spaces/rcfeng/KEEP.

Question about training code release

Hi all, we've released the training code

TypeError: 'tuple' object does not support item assignment

Hi, this message suggests `opt` is a `tuple` instance here. This could stem from the incompatible version of `basicsr`. Did you run `python setup.py develop` as suggested in the installation?

Request for the detail opt of degradations

We've release the yaml files