Some Questions about Reproducing Experimental Results

[junjie1003]

I have faithfully followed the README instructions to reproduce the experiment, selecting the target attribute as "StraightHair". However, the baseline and final training results are as follows:


This is the improvement over baseline:

When comparing them to the results mentioned in the paper, I notice a significant difference in terms of both metrics and improvement levels:


How can I address this issue?

[junjie1003]

I have followed the README instructions throughout the entire process, without making any changes to the parameters. The command I used for running the experiment is as follows:

    python generate_images.py --experiment orig
    
    python main.py --experiment baseline --attribute 20
    python get_scores.py --attribute 20
    
    python main.py --experiment baseline --attribute 32
    python get_scores.py --attribute 32
    
    python linear.py --attribute 32
    python generate_images.py --experiment pair --attribute 32
    python get_scores.py --attribute 32 --out_file data/fake_images/Straight_Hair_scores.pkl
    python main.py --experiment model --attribute 32
    ```
I don't understand where the problem lies. Could it be due to differences in the experimental environment?