luo_13

When training the VOC dataset（train 07+12trainval, test 07 test）, the performance of using imagenet pre-trained model instead of using coco is much worse. Has anyone tried it?

about Contrastive Loss

1

Hi, thanks for your great work! I have a question about contrastive loss. What does (Ypos, Yneg, Yanchor) stand for?

Any pretrained models or test code?

7

Great work! Can you provide the test code and pre-training model? @raywzy

The generated frame is blurrier than the original frame

1

I tested 8x interpolation using IFRNet_GoPro.pth and found that although the generated frames have good coherence, the generated frames are blurrier than the original frames. Why is this?

标注人员jsons

1

你好，感谢开发这一标注工具！ 请问一下，标注人员所对应的json文件是否需要自己生成？

About Image Input and Output.

1

I have a few questions and concerns. I have a denoising model where I preprocess the input by dividing it by 255 and postprocess the output by multiplying it by...