HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Network Pruning On Imagenet

평가 지표

Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

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

0 of 16 row(s) selected.