Table 6 Comparisons of average accuracies (%) against two feature extraction network for retrosynthesis on the USPTO-50k dataset
From: CNN-based two-branch multi-scale feature extraction network for retrosynthesis prediction
Model | Top-k accuracy % | |||
|---|---|---|---|---|
1 | 3 | 5 | 10 | |
TextCNN | 21.6 | 39.9 | 43.9 | 53.9 |
CNN-TMN | 61.1 | 79.1 | 83.9 | 87.7 |