Junlin Han

> @JunlinHan If possible, can you please share the dataset you used for training ? Also which code did you try, 1 or 2 ? Hi, I used both PASCAL...

> Do you train with the dataset images as they are or do some pre-processing. I basically wanted to know if I should black out all the non-contour pixels or...

Hi hai, Yes, it is possible. Please modify --load_size 286 --crop_size 256 (default setting) to your desired resolution.

HelloShenZheng, Sorry for my late reply. Please check this part:   **

Hello, thanks for your nice words! Simply resize them to the same resolution should be fine.

Hi 您好，可以的。 下好task III的数据集然后加入test set就好，否则可能需要修改一下代码。

Hello! Many thanks for your question! The size during training/testing is in 256 * 256. For better visualizations we resized them to a different size , which should match the...

Regrettably, I've transitioned to new organizations and no longer have access to the previous clusters. To proceed, you can either refer to the paper for reporting their results or undertake...

Hello, Yes, the result can be bad when performing underwater image enhancement tasks. Please try this CWR pre-trained on HICRD, fine-tuned on UIEB: https://drive.google.com/file/d/1MCYZcAjKAf3y_rSNes_Fs3tm7L0U_77e/view?usp=sharing

> > Hello, Yes, the result can be bad when performing underwater image enhancement tasks. Please try this CWR pre-trained on HICRD, fine-tuned on UIEB: https://drive.google.com/file/d/1MCYZcAjKAf3y_rSNes_Fs3tm7L0U_77e/view?usp=sharing > > Sorry, did...