FoundationVision
FID results of GPT-L and GPT-1B on 256*256 images
Hi, thanks for the excellent work. I'm trying to reproduce the results on 256*256 images. The VQGAN model is reproduced successively, achieving $2.10$ rFID. However, the AR part experiences a significant performance gap. More specifically, I use 8 A100-80G GPU to run the following scripts
bash scripts/autoregressive/train_c2i.sh --cloud-save-path xxx --code-path xxx --gpt-model GPT-L --epochs 50
bash scripts/autoregressive/train_c2i.sh --cloud-save-path xxx --code-path xxx --gpt-model GPT-1B --epochs 50
The training results are as follows
| Model | Final Loss | FID | Expected FID |
|---|---|---|---|
| GPT-L | 7.86 | 4.62 | 4.22 |
| GPT-1B | 7.33 | 4.13 | 3.09 |
Is the final loss reasonable? Do you have any idea what the reason might be?
Thanks!
Hi~ I don’t understand what is reproducing the result on 224x224. The expected FID is in 256x256.
Hi~ I don’t understand what is reproducing the result on 224x224. The expected FID is in 256x256.
Sorry for the mistake. I was trying to emphasize that the image resolution is not 384x384, but I mistakenly wrote 224.
Hi~ I don’t understand what is reproducing the result on 224x224. The expected FID is in 256x256.
Hi. Thank you for this awesome repo. I have the same issue with the original code that the loss ends around 7.3 after 300 epochs.
Hi~ I don’t understand what is reproducing the result on 224x224. The expected FID is in 256x256.
Hi. Thank you for this awesome repo. I have the same issue with the original code that the loss ends around 7.3 after 300 epochs.
Hello, I would like to ask you what machine and how much training time are needed to get the results shown in the figure.
Hi~ I don’t understand what is reproducing the result on 224x224. The expected FID is in 256x256.
Hi. Thank you for this awesome repo. I have the same issue with the original code that the loss ends around 7.3 after 300 epochs.
Hello, I would like to ask what the model size for this loss curve is and the FID you calculate. Thanks!
