Image Classification on CIFAR-100 (Pruning Error Analysis)
31.88Baseline ErrorTwo-Phase Pruning
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Two-Phase PruningCNN architecture=ResNet562026.04 | 31.88 | 32.84 | 0.86 | 22.13 | |
| Two-Phase PruningCNN architecture=ResNet1102026.04 | 36.62 | 37.89 | 1.27 | 20.62 | |
| Bi-CNN-PruningCNN architecture=ResNet562026.04 | 41.86 | 24.83 | -17.03 | 16.38 | |
| DeepPruningESCNN architecture=ResNet562026.04 | 41.94 | 40.2 | -1.74 | 16.18 | |
| DeepPruningESCNN architecture=ResNet1102026.04 | 50.17 | 50.98 | 0.81 | 17.78 | |
| Bi-CNN-PruningCNN architecture=ResNet1102026.04 | 50.47 | 38.44 | -12.03 | 18.13 |