llu025 / heterogeneous_cd Goto Github PK

Dear Dr.Luppino
Regarding the steps of code running, can there be a more detailed description

Dear Dr.Luppino,
Thank you for sharing the code and data.
Please tell me what the preprocessing of the UiT_HCD_California_2017.mat did you do? I want to know how to get the UiT_HCD_California_2017.mat, but when I made the SAR data by myself using SNAP6.0 , it cannot achieve your data effect , neither terrain correction nor the removing outliers.
"First, both the images are clipped to remove outliers: for every channel, the minimum (maximum) is set equal to the mean - (+) 3 times the standard deviation. Every value below (above) such threshold is clipped up (down) to the minimum (maximum). Then, all the data in this dataset are normalised between -1 and 1."
Thank you very much!

Dear Dr.Luppino,
When I ran the X-net.py for the Texas dataset, an error occurred: FileNotFoundError: [Errno 2] No such file or directory: 'data/Texas/change-prior.mat'. Could you provide me with change-prior.mat? And how to construct the mat file?
Thank you very much!
Aiye

Dear author,
hi! For the Texas dataset, X-Net and ACE-Net will debug each time when they train to 80/240, as shown in the figure. Could you help me with this problem? Thank you very much!

Dear Dr.Luppino,

Sorry to bother you. I want to ask a small issue: Is the change prior calculation of change_priors.py can be understood same as the change prior calculation in your another paper "Deep Image Translation with an Affinity-Based Change Prior for Unsupervised Multimodal Change Detection" TGRS2021? I read change_priors.py and find it shares similar steps with the change prior method in TGRS2021 paper. which paper do you recommend to be cited if I use change_priors.py?

Hope for your reply.

Greetings! Thank you very much for your contribution to the various algorithms in the open source Heterogeneous_CD project! However, the cGAN.py file in the Code-Aligned_Autoencoders project does not run properly to obtain results.
For example, the California dataset was used as requested, and when the cGAN.py file is run, a dimensionality inconsistency occurs at the 12th epoch of training, as shown below:

The same situation occurs when using multiple other datasets.
I would like to express my thanks again and hope to get your reply and answer!😀

Dear Dr.Luppino,
Can you tell me the excuted environment of these codes and the version of tensorflow ？
Thanks！

I am so interesting in your project,can you provide the datasets. my email:[email protected] . Thank you very much.

Thank you for sharing your code and dataset! I couldn't find any code for calculating the prior transformation information in Code_Aligned.py. Did I miss something?

Dear Dr.Luppino,
How to produce the file Texas_super_test.mat in folder legacy\image regression\GPR_Texas.py?
I did not find the mat file in your code.

Dear Dr.Luppino,
When I am running Code_Aligned_Autoencoders.py, I find that after the final epoch, the 'ACC' obtained by final_evaluate() is much higher than that in the historical last epoch(such as the 'ACC' increases from 0.783 to 0.928 in this picture and I set 21 as the final epoch). Do you know the reason? It is strange.
Thank you!

Hello author, thank you very much for open-sourcing the code for the TGRS paper, I've encountered some problems in reproducing your work, you mentioned in your paper that the prior is obtained by calculating and then averaging over three different scales, but is the implementation strategy in your actual code inconsistent with the instructions in your paper?
For example, you are using three images in your code that are zoomed in 2x, the original image, and zoomed out 2x to calculate the prior at a patch_size of 20, but that's what you wrote in your paper

I'd like to ask which of these two strategies works better in your work?
Looking forward to your reply very much!

Dear Dr.Luppino,
When I ran the program cGAN.py in the folder Code-Aligned_Autoencoders, an error occurred as follows:

C:/pythoncd/Heterogeneous_CD/Code-Aligned_Autoencoders/cGAN.py:175 _train_step  *
    targets = [item for item in sublist for sublist in targets]

NameError: name 'sublist' is not defined

Could you tell me how to solve the problem?
Thank you very much!
Aiye

Hi! Thanks to your amazing work！I have noticed your code is tensorflow version, have your try a pytorch version?

When I use this command docker pull madsadrian/tensorflow:latest, it has this problem 'Got permission denied while trying to connect to the Docker daemon socket at unix:///var/run/docker.sock: Post "http://%2Fvar%2Frun%2Fdocker.sock/v1.24/images/create?fromImage=madsadrian%2Ftensorflow&tag=latest": dial unix /var/run/docker.sock: connect: permission denied'

Dear Dr.Luppino,
Thank you for sharing the code and data.

I found Texas and California dataset, but shuguang dataest didn't.
Could you please provide the download website of shuguang dataest?

Thank you very much!

Hi Dr.Luppino,

Thank you for sharing so nice work and code. I am doing similar work and want to compare it with your results. But unfortunately, I am not familiar with TensorFlow. When I try to use your code to process images with more than three channels, there always have a problem in "tmp2 = tf.concat Line 76 of decorators.py". Could you give me help with parameter setting? and I try to get the whole resolution change map from here " change_map = self._change_map(difference_img)" line 248 of change_dtector.py. But the image I got is very small, I don't know how to do it. Hope you can give me some tips~

Best regards,
yusin

Dear Dr.Luppino
Thank you for sharing your code and dataset! While attempting to access the Texas dataset, I noticed that the provided website is not available. I'm curious to know if the link will be fixed in the future or if there is an alternative method to obtain this dataset. Thank you once again!