FFA-Net icon indicating copy to clipboard operation
FFA-Net copied to clipboard

FFA-Net: Feature Fusion Attention Network for Single Image Dehazing

Results 22 FFA-Net issues
Sort by recently updated
recently updated
newest added

If I use my own dataset for training, do I not need the model trained by the author before? Thanks very much!

请问在室外场景的训练集、测试集中,RESIDE数据集给出的室外场景OTS训练集和室外场景测试集SOTS是有重叠的,您是如何解决的这个问题?

hi,The test input is the pre-processing result after normalization( tfs.Normalize(mean=[0.64, 0.6, 0.58],std=[0.14,0.15, 0.152])), while the output needs to be de-normalized to get the RGB image with the output pixel value...

Hello, I want to ask how to visualize the attention map. Thanks

I am sorry to disturb you again. "The number of Group Structure G is 3. In each Group Structure, we set the Basic Block Structure number as B = 19."...

我用作者提供的代码在我的设备上运行main.py,报错内存不足,只有当我把batchsize设置为1时才能运行成功,但是我用的时TeslaV100 32G显卡,作者用的是2080Ti,作者设置的batchsize是16,为什么我的会内存不足呢,有同学遇到这个问题吗

我不知道是上传的代码版本有问题还是别的原因,但是DataLoader确实有问题,它没有返回hazy and gt, 而是hazy和正则化的hazy(名字为clear)。 这就是为什么指标很好,但是视觉上看没有效果的原因:因为dataloader的问题,模型拟合的目标一开始就是错的。 Error in class dataloader , it should return hazy image and clear image, but dataloader returns normalized hazy image and hazy image. This is why...

Add commands for more comprehend usage