Table 5 Results of different thawing training methods.
From: Counterclockwise block-by-block knowledge distillation for neural network compression
Freeze? | CIFAR-10 | Tiny-imagenet-200 | ||
|---|---|---|---|---|
VGG-16 (88.5%) | Resnet-18 (85.0%) | VGG-16 (59.4%) | Resnet-18 (57.3%) | |
No | 85.8% | 82.4% | 55.9% | 54.2% |
Yes(lr*0.1) | 86.5% | 83.4% | 57.9% | 55.0% |
Yes(lr*0.25) | 87.3% | 84.8% | 58.7% | 55.2% |
Yes(lr) | 88.2% | 85.6% | 59.4% | 55.7% |
