Top-1 Accuracy: 75.64
Papers with Code · CC BY-SA 4.0
Network Pruning
Network Pruning is a popular approach to reduce a heavy network to obtain a light-weight form by removing redundancy in the heavy network. In this approach, a complex over-parameterized network is first trained, then pruned based on come criterions, and finally fine-tuned to achieve comparable performance with reduced parameters.
<span class="description-source">Source: Ensemble Knowledge Distillation for Learning Improved and Efficient Networks </span>
논문
Accuracy: 77.1
Accuracy: 76.20GFLOPs: 2.3
Accuracy: 78.79GFLOPs: 2.335MParams: 14.811
Accuracy: 77.97GFLOPs: 1.588MParams: 9.3
Accuracy: 78.0GFLOPs: 2.5
Top-1 Accuracy: 74.31
Top-1 Accuracy: 76.03
Accuracy: 74.01
Top-1 Accuracy: 74
Top-1 Accuracy: 74.68
Top-1 Accuracy: 76.93
Accuracy: 75.59
Inference Time (ms): 675.56
Top-1 Accuracy: 76.17
Accuracy: 57.5%MParams: 1.24
Top-1 Accuracy: 75.5