igashov / RetroBridge

RetroBridge: Markov Bridge Model for Retrosynthesis Planning
Other
27 stars 2 forks source link

Question about reproduced results on USPTO-50k #5

Open YifaSuoha962 opened 1 month ago

YifaSuoha962 commented 1 month ago

Sorry for bothering you. I have reproduced your work several times, including using the pre-trained model you provided in https://github.com/igashov/RetroBridge/blob/main/configs/retrobridge.yaml as well as retraining the model with the best parameters you suggested (the batch_size is compressed to 32 due to limitation of GPU memory). The following tables show our experimental results. Though the round-trip accuracy is on par with the published results, the exact match accuracy is significantly lower than what was reported.

Round-Trip Accuracy on USPTO-50k (%) Top-1 Top-3 Top-5 Top-10
Retrobridge (directly evaluate the offered checkpoint) 83.96 72.75 70.47 70.22
Retrobridge (re-train from scratch, batch-size: 32) 83.66 72.46 69.81 69.40
Exact Match Accuracy on USPTO-50k (%) Top-1 Top-3 Top-5 Top-10
Retrobridge (directly evaluate the offered checkpoint) 47.79 67.01 71.28 73.74
Retrobridge (re-train from scratch, batch-size: 32) 48.37 66.95 70.94 72.82

I wonder whether there is something different from the hyperparameter setting of your best model, or is there something wrong in the evaluation codes?