wtliao / text2image

Text to Image Generation with Semantic-Spatial Aware GAN
179 stars 34 forks source link

FID score in COCO #18

Open LeaFoRin opened 2 years ago

LeaFoRin commented 2 years ago

Hello,I test the trained models from your onedrive in COCO,the FID score is 28.1929. It has a big gap with the paper data (19.37) . My FID code is from https://github.com/bioinf-jku/TTUR and my GPU is 4 3090 . I'm confused about this and want to know the parameters that your FID code sets about COCO, such as the image size of groundtruth,whether or not you split the coco data and so on.Thanks

QinSY123 commented 2 years ago

I have tested the valid dataset on COCO2014, and the FID score is 18.18. However, the visualization results are not ideal.