I tried to train a ViT-GAN model (from this repo) on my database, where i have images as input and output. The input image is a PNG map of a path planning problem. Red channel is obstacle map, green and blue is one pixel with start/goal. The output image would be the planned path on the red channel and this is what i am trying to teach the model. The model from the repo works nicely on the included examples and that is a much more complex problem than mine, so i naturally thought this network would solve my problem without much further tuning.

I tried to train a ViT-GAN model (from this repo) on my database, where i have images as input and output. The input image is a PNG map of a path planning problem. Red channel is obstacle map, green and blue is one pixel with start/goal. The output image would be the planned path on the red channel and this is what i am trying to teach the model. The model from the repo works nicely on the included examples and that is a much more complex problem than mine, so i naturally thought this network would solve my problem without much further tuning.