ResNet50-2.3 GFLOPs

Reported on 3 benchmarks across 1 task · 1 paper · 3 SOTA

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

Methodology3 results

Network PruningonImageNet
Accuracy· 2016-08-31
78.79
SOTA
Pruning Filters for Efficient ConvNets arXiv:1608.08710
Network PruningonImageNet
GFLOPs· 2016-08-31
2.335
best: 2.5 (ResNet50 2.5 GFLOPS)
SOTA
Pruning Filters for Efficient ConvNets arXiv:1608.08710
Network PruningonImageNet
MParams· 2016-08-31
14.811
SOTA
Pruning Filters for Efficient ConvNets arXiv:1608.08710