Can not reproduct the result in Table 2.

[Zyriix]

I run the following training command on 8 v100.

torchrun --standalone --nproc_per_node=8 train.py --outdir=training-runs
--data=datasets/cifar10-32x32.zip --cond=0 --arch=ddpmpp

This gives me a FID at 2.08169 which is still far from FID in the paper(1.97).

I think this may caused by the random seeds(Random init in the code).
Is it possible to share the seed for reprodcuting the result in table2?

Any suggestiones?

[Newbeeer]

I observed the FID of EDM fluctuates largely. Did you report the lowest FID among checkpoints?

[Zyriix]

I observed the FID of EDM fluctuates largely. Did you report the lowest FID among checkpoints?

I found this in some papers that try to retrain Edm. I got the lowest FID(2.04053) at around 16w ckpt.
I think the fluctuation is caused by lower ema rate and larger learning rate.

[yuanzhi-zhu]

@Zyriix To calculate FID we have to first generate, saying 50000 samples. The random seed can influence the generation process of these samples hence the FID value I guess

[Zyriix]

@Zyriix To calculate FID we have to first generate, saying 50000 samples. The random seed can influence the generation process of these samples hence the FID value I guess

Most works use the same sample seeds just like this repo:
049999, 5000099999, 100000~149999
and report the lowest one.

[Liyuan-Liu]

--arch=ncsnpp performs much better than VP architecture