Network Pruning On Imagenet
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy |
|---|---|
| eagleeye-fast-sub-net-evaluation-for | 70.7 |
| pruning-filters-for-efficient-convnets | 78.79 |
| eagleeye-fast-sub-net-evaluation-for | 74.2 |
| eagleeye-fast-sub-net-evaluation-for | 74.2 |
| pruning-filters-for-efficient-convnets | 78.07 |
| network-pruning-via-transformable | 76.20 |
| ac-dc-alternating-compressed-decompressed | 73.14 |
| eagleeye-fast-sub-net-evaluation-for | 76.4 |
| pruning-filters-for-efficient-convnets | 76.376 |
| squeezenet-alexnet-level-accuracy-with-50x | 57.5% |
| group-fisher-pruning-for-practical-network | 77.97 |
| eagleeye-fast-sub-net-evaluation-for | 77.1 |
| knapsack-pruning-with-inner-distillation | 77.70 |
| knapsack-pruning-with-inner-distillation | 78.0 |
| network-pruning-that-matters-a-case-study-on-1 | 75.59 |
| group-fisher-pruning-for-practical-network | 73.42 |