ResNet50 2.0 GFLOPS

Reported on 2 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology2 results

Network PruningonImageNet
Accuracy· 2020-02-19
77.7
best: 78.79 (ResNet50-2.3 GFLOPs)
Knapsack Pruning with Inner Distillation arXiv:2002.08258
Network PruningonImageNet
GFLOPs· 2020-02-19
2
best: 2.5 (ResNet50 2.5 GFLOPS)
Knapsack Pruning with Inner Distillation arXiv:2002.08258