Closed HamzaJavaid-gh closed 8 months ago
Thanks for your asking. It is very strange that loss cannot decrease in both labeling (e.g., r1 or r3). Could you provide more detailed information? Also, try using pre-trained weights (e.g., ImageNet), which will accelerate convergence.
I've tried similar training data with r3, but if we can reproduce your results so if its possible to release the training data? That'd be very helpful
Thanks for your attention. The training dataset will be released soon.
The training dataset can be downloaded from the following link. Due to Google Drive's capacity limitations, we are currently only able to share it via Baidu Pan: https://pan.baidu.com/s/1ZgSiNX_Dd7cZcwiHv1ujVg?pwd=h4p7
Hi!
I'm trying to train a custom dataset with your network with COCO and stable diffusion subset each 200K images. I tried with the r1 i.e [Real, Synthetic] with 0,1 labels in the text file ,first but the loss is not dropping.
Then I tried to divide my data with r3 [Real, Synthetic, Real Painting, Synthetic Painting] each 200k images and assigned them labels of 0,1,2,3 accordingly. The loss increased instead with same BS. I see maybe there is some confusion in how to prepare the training file with labels. Can you provide a sample training txt file with image paths?
Thanks in advance