Cannot get the results in paper

[daaiwoni]

I did test as the following steps, but cannot get the same results in paper.
Is there anything wrong in my steps?

My steps

1. from the OneDrive location dire/test/lsun_bedroom/lsun_bedroom, I downloaded the real dire images real.tar.gz and unpacked them into data/test/lsun_adm_data/0_real. This set has 1000 JPG images.
2. from the OneDrive location dire/test/lsun_bedroom/lsun_bedroom, I downloaded the fake dire images adm.tar.gz and unpacked them into data/test/lsun_adm_data/1_fake. This set has 1000 PNG images
3. I downloaded the model checkpoints/lsun_adm.pth from OneDrive and put it in the folder data/exp/test_model/ckpt
4. I ran test.py by the following command:
   python test.py --gpus 0 --ckpt lsun_adm.pth --exp_name test_model datasets_test lsun_adm_data.
   This command pointed to the the downloaded model and lsun_adm dataset.

My results

Here is the result I got by the command:

'test_model:lsun_adm' model testing on...
lsun_adm_data:
ACC: 0.89900
AP: 0.99890
R_ACC: 0.79800
F_ACC: 1.00000

These results are different from those in paper. Is there anything wrong in my steps?

My configurations

CPU : Intel(R) Xeon(R) Silver 4210R CPU @ 2.40GHz
GPU : NVIDIA Corporation TU104GL [Tesla T4]
System : 20.04.1-Ubuntu SMP
python : 3.8.18
torch : 2.0.0
cuda : 11.7

[zg-L7]

@daaiwoni My steps are the same as yours, and the result is：
'lsun_adm_release:lsun_adm' model testing on...
lsun_adm_data:
ACC: 0.89850
AP: 0.99890
R_ACC: 0.79700
F_ACC: 1.00000

[AlbertWYP]

My steps are the same as yours, and the result is：
TestSet,ACC,AP,R_ACC,F_ACC
lsun_adm,0.8976666666666666,0.9988908105586686,0.693,1.0
Have you found the cause of the problem？

[aditipanda]

I used dire images with test.py and got almost same results as Table 3 of the paper.

You can't use original images - see #7 to understand how to compute-dire and then test.