Network Pruning On Imagenet

Metriken

Accuracy

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

		Paper Title
ResNet50-2.3 GFLOPs	78.79	Pruning Filters for Efficient ConvNets
ResNet50-1.5 GFLOPs	78.07	Pruning Filters for Efficient ConvNets
ResNet50 2.5 GFLOPS	78.0	Knapsack Pruning with Inner Distillation
RegX-1.6G	77.97	Group Fisher Pruning for Practical Network Compression
ResNet50 2.0 GFLOPS	77.70	Knapsack Pruning with Inner Distillation
ResNet50-3G FLOPs	77.1	EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning
ResNet50-2G FLOPs	76.4	EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning
ResNet50-1G FLOPs	76.376	Pruning Filters for Efficient ConvNets
TAS-pruned ResNet-50	76.20	Network Pruning via Transformable Architecture Search
ResNet50	75.59	Network Pruning That Matters: A Case Study on Retraining Variants
ResNet50-1G FLOPs	74.2	EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning
ResNet50-1G FLOPs	74.2	EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning
MobileNetV2	73.42	Group Fisher Pruning for Practical Network Compression
ResNet50	73.14	AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks
MobileNetV1-50% FLOPs	70.7	EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning
SqueezeNet (6-bit Deep Compression)	57.5%	SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

0 of 16 row(s) selected.

Network Pruning On Imagenet | SOTA | HyperAI