ResNet50-1G FLOPs

Reported on 3 benchmarks across 1 task · 2 papers

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

Methodology5 results

Network PruningonImageNet
Accuracy· 2020-07-06
74.2
best: 78.79 (ResNet50-2.3 GFLOPs)
EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning arXiv:2007.02491
Network PruningonImageNet
Accuracy· 2020-07-06
74.2
best: 78.79 (ResNet50-2.3 GFLOPs)
EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning arXiv:2007.02491
Network PruningonImageNet
Accuracy· 2016-08-31
76.376
best: 78.79 (ResNet50-2.3 GFLOPs)
Pruning Filters for Efficient ConvNets arXiv:1608.08710
Network PruningonImageNet
GFLOPs· 2016-08-31
1.075
best: 2.5 (ResNet50 2.5 GFLOPS)
Pruning Filters for Efficient ConvNets arXiv:1608.08710
Network PruningonImageNet
MParams· 2016-08-31
6.954
best: 14.811 (ResNet50-2.3 GFLOPs)
Pruning Filters for Efficient ConvNets arXiv:1608.08710