Open yezer24 opened 2 years ago
Hey @yezer24, sorry for the late response. For training, you can run evo_train.py. The setup.sh script should be able to get a working environment setup, but due to the dependencies of AutoGAN the environment setup is a bit tricky. I believe IS and FID values are calculated during training to select the most optimal model. Let me know if you have any other questions.
Dear professor, may I ask if you used the configuration file in the paper to configure the AutoGan environment before? After configuring EvoGan's environment, it didn't work, so I went back to AutoGan and still couldn't get the code running. Could you please tell me the name and version of the specific configuration environment package as well as the training process? Our research group is very interested in your article. Thank you very much.
Hey @fly2tortoise, I will take a look. Could you please share the error you are getting.
Dear Professor
I re-created the new environment of evogan1,Strictly follow the source setup.sh to match the environment.
There were some problems running the code(python evo_train.py).
After I looked up some information, it seems to be the gzip file part of the problem.
Could you please tell me how to modify this part? I stopped when I was training EPOCH0 .
Thank you for taking the time out of your busy schedule to answer my simple question. I really appreciate it.
Some simple questions.docx
Hey @fly2tortoise, I will try to get an environment working and get back to you by Monday. Thanks for sending me the details.
Thank you. That was a big help. Looking forward to your reply
Hey @fly2tortoise, still haven't figured out a solution. I'm trying to find a working environment. AutoGAN is running a very old PyTorch environment, so it is taking me some time to find a working solution.
Thank you, dear professor. I'm still trying to debug it, but it still doesn't work. In the future, I also use evolutionary algorithms to study GAN networks, and professor's work has great inspiration for me .
Distinguished Researcher Once I had configured the environment, I started evo_train.py after an afternoon of training. IS size IS 1.455, FID size IS None, what IS wrong with me? I think there is something wrong with me. The network is not working. Looking forward to your reply, thank you very much
Hello, I am very interested in your paper. I would like to learn more about the execution steps of the code. Can you describe the training process in detail?How to get the final structure searched out, and further train it to calculate its IS and FID values, thank you.