Thank you for sharing your excellent paper and the complete codebase. We have a question regarding the reproduction and would greatly appreciate your guidance.
After following the instructions by running python run.py -p test -c config/ours_sigmoid.json and fixing several bugs, we observed an MAE of between 0.8674 and 0.9696 on the testing set, which is significantly higher than expected and reported. Could you kindly confirm if the code used for evaluation is accurate and whether the checkpoints are up-to-date?
Below are the changes we made to ensure execution.
Comment on all the code that causes syntax errors.
Change the data_root in configs/ours_sigmoid.json from pmaa to PMAA (where our data is)
Change and correct the package name in /models/network_x0_dpm_solver.
Add alpha_t = alpha_t[:,None, None,None] and sigma_t = sigma_t[:,None, None,None] in core/dpm_solver_pytorch.py Line 292.
We look forward to your feedback and thank you in advance for your assistance.