gligen / GLIGEN

Open-Set Grounded Text-to-Image Generation
MIT License
1.99k stars 150 forks source link

Training 200000iters on 3000 image dataset, but boxes had no control effect #97

Open Hui-88 opened 6 hours ago

Hui-88 commented 6 hours ago

Thank you for sharing. I have a question to ask you. I trained 200000 iters on my own dataset of 3000 images, with batch_size=2. The box coordinates in the tsv file are the top left and width height, but there was no layout control effect after training. Excuse me, is the dataset too small? Do I need to add iters. look forward to your reply!

Hui-88 commented 5 hours ago

1