LaraNeves

I'm facing the same problem where the training images on Tensorboard look like:  While the images from the validation set (which was built exactly like the training set) look...

@michielva thank you for the update, it's helpful to discuss this issue and know that I'm not alone in this. So I've also been digging around the Object Detection API...

@ophirSarusi Thank you for your suggestion, I did try it however correct me if I'm wrong but I think that those kinds of conversions are only happening in the data...

So with the exact same dataset: - generated with TF 2.2 according to the object detection api tutorials - where my original images were cropped into 1000x1000 cropped images around...