Yang7879 / 3D-RecGAN

🔥3D-RecGAN in Tensorflow (ICCV Workshops 2017)
https://arxiv.org/abs/1708.07969
MIT License
131 stars 38 forks source link

nothing in folder train_mod #7

Open 254788 opened 4 years ago

254788 commented 4 years ago

Hello, when I was studying your thesis(《3D Object Reconstruction from a Single Depth View with Adversarial Learning》), I found that the code could not be run. Can you describe how to use it? I downloaded your github code and installed the conda environment on win10. After running, nothing is generated in the folder train_mod. In addition, which parameter can be modified to be smaller, the computer speed is very slow. Thank you for your answer!

Yang7879 commented 4 years ago

Hi @254788 , make sure the virtual environment is correct before running the code. To speed up the code, you are suggested to modify the latent vector to be a smaller dimension, eg. reduce 5000 to 500 in the below line.

https://github.com/Yang7879/3D-RecGAN/blob/07c3f08c36f2567349ee695ca16ce0377aef2bd9/main_3D-RecGAN.py#L68