Open lanchen2019 opened 1 year ago
The model is trained on mostly sedans (certainly not trucks). Training models on larger datasets or augmented data might make it work better for your input.
Thanks a lot and congratulations! Hope the training code will be released soon thus I will train on other datasets.
Hi, Thanks for releasing your code and model! I tried to test new edge images but get similar results. This is the input,
and these are outputs
The generated video cannot align well with the input edge image. The command is "python applications/generate_video.py --network checkpoints/pix2pix3d_edge2car.pkl --outdir examples --random_seed 1 --cfg edge2car --input examples/edge2car2.png". What is your suggestion for generating better results? Best Wishes