Jinkun Huang

Some questions

4

Hi! I would like to ask if the parameters of the pre-trained model you provided were converted from the original author's tensorflow version? Then can you provide the relevant training...

your training set

1

Hi! Thank you for sharing your code! I found that the training set of your model in your paper uses the DIV2k dataset, but the training set of this dataset...

Something about loss function.

2

Thank you for sharing your code! But I find out that the hyperparameter of loss function(lamda_reconstruction and lamda_low_frequency) in your code is different from the paper, which one I should...

ssim计算问题

1

https://github.com/pkuxmq/Invertible-Image-Rescaling/blob/93aaa943a96073fd431ac55f12abe717841b26c4/codes/utils/util.py#L167-L185 计算ssim这里的第180行是不是写错了？处理3通道图片的时候

baseline in paper

1

Hello! I read the paper you published in ICMR19 and now I am planning to reproduce your model and the baseline mentioned in your paper in our work.I would like...

Hello! I have a few questions. 1. how to set the corresponding bpp。 2. is it possible to raise bpp above 1? 3. how should I set it in my...

About dataset txt file and training

3

Hello! I realized that the txt files of the datasets are not provided in your code, especially the test datasets (e.g. CASIA, NIST), which makes it impossible for me to...