Trained on over 15000 images and still getting lackluster results

I'm training the model on over 15000 images but it's still outputting final test images like the one below:


I'm running the following command:

`python main.py --data_dir dataset --dataset food --input_height 128 --output_height 128 --train`

What can I do to get better results??

Start by reading main.py and reproducing the provided training command with the dataset and image dimensions stated in the issue. Compare the resulting output with the attached train_00006000 image. The issue does not define a specific code change or measurable result, so the expected meaning of “better results” would need clarification before work can be considered done.

Written by the indexing model from the issue text.