this is the code is written in pytorch in the dataset preparation step as you can see
screen shot of the code
and here are some metrics the trained model is unet model with early stopping
[loss plotone of the metrics](https://i.sstatic.net/McfukUpB.png)
my goal is to know what is the impact of converting the images is it for the performance ? or what exactly ?
New contributor
Faiçal AMMI SAID is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.