dingyan1478

训练模型的问题

1

 您好，在去雾网络中，我按照您默认的通道数进行训练，可以我训练得到的模型的大小为240M左右，但您提供的预训练模型的大小为80M左右，你能告诉是为什么吗？或许您在保存模型的时候使用了什么样的策略来压缩模型吗？

Train

3

Hi! Thank you for your work! You only provided the training code for image denoising. It's convenient to ask how to train low illumination images?

为什么不能复现论文中的结果呢？

2

我使用了作者提供的训练模型，但是复现出的结果还是很差，想知道在test_one_image.py中的gt_image_path是什么？在测试的时候不是应该输入测试图片，然后加载模型就可以了吗？ 谢谢啦

关于训练的问题

2

您好！ 感谢您的工作，我有一个疑问，如果我不使用多进程进行训练的话，我应该如何设置这条命令呢“python -m torch.distributed.launch --nproc_per_node=8 --master_port=4321 basicsr/t.py -opt options/train/GoPro/HINet.yml --launcher pytorch”？ 现在我设置的一直在报错，非常期待能够得到您的回复！

Thank you for your great work. I don't know if it's convenient for you to provide the code of your training process?

Thank you for your dedication. Will you publish train.py?

code

1

Hello, thank you for your great work! I'd like to know when your version of Pytorch code will be released?

Sorry to disturb you again! How do you calculate PSNR? I use the model and data set provided by you for training, but the final test result is not as...

Code

2

Hello! Thank you for your great work. I'd like to know where you found GDCP, I haven't found the relevant code. If you can, could you please provide one? Thank...

Datasets

4

Hi! In the paper, it is said that the estimated transmission map sent to the media transmission network is reversed, but why do I feel that the image in folder...