wrong ACC/AP in SD-v1

[baiqingookii]

I used lsun_pndm.pth and test on lsun/lsun/sdv1,but got
lsun_lsun_sdv1:
ACC: 1.00000
AP: 1.00000
R_ACC: 1.00000
F_ACC: 1.00000
,and I train the model used the dataset and got the same result.but the paper says the result is 89.4/99.9.Does anyone have the same result with me?

[LoreImbo]

I used lsun_pndm.pth and test on lsun/lsun/sdv1,but got lsun_lsun_sdv1: ACC: 1.00000 AP: 1.00000 R_ACC: 1.00000 F_ACC: 1.00000 ,and I train the model used the dataset and got the same result.but the paper says the result is 89.4/99.9.Does anyone have the same result with me?

I had the same results, not only with the ckpt lsun_pndm.pth, but also with lsun_adm.pth and lsun_iddpm.pth.
I think it is a problem with the entire dataset or maybe an incorrect transcription of the results on the paper.
I attach a screen with the results.
Ckpt ADM

Ckpt PNDM

Ckpt IDDPM