Xingang Pan

I suggesting first performing joint pretraining on more samples (like 200 samples), and then train for each instance. This is what we did for face data.

@leonel-os It seems that your machine has only 1 GPU, while our scripts require at least 4 GPUs. You need to revise the `run_car.sh` script accordingly to run on one...

@Minsoo2022 Hi, thanks for your interest. The provided latent code here is obtained by performing GAN inversion to the testing images. Thus, there could still be some notable differences between...

@Minsoo2022 Yes, you are right. pt_file['img'] and the generated image from pt_file['latent'] should be same. It seems there is some inconsistency. Could you please try using truncation=0.7 and see if...

Sorry about the delay. I will reply to you tomorrow.

Hi, I have uploaded my GAN inversion code here: https://drive.google.com/file/d/1pCfnDiHZNnRoEVZ4RhcLfZyPrJgUWEYk/view?usp=sharing You may check it out and perform the inversion to get the latent code :-)

Due to some limitations of colab, I am not planning to make a colab version recently. But I do hope to make this code work well. So feel free to...

@molo32 It seems that you have pytorch1.7, which neural_renderer_pytorch does not support by default. You may try pytorch1.1 or 1.2. I'll try to add support to pytorch1.7.

@molo32 I have checked the code of neural_renderer_pytorch, which does not support pytorch1.7 for now. To make it fit with pytorch1.7, you meed to switch to 'at_assert_fix' branch, change the...

@molo32 For the case of pytorch = 1.2.0, it seems you need to change the value of 'PORT' in the script to another value. Also make sure you have at...