HyperAIHyperAI

Command Palette

Search for a command to run...

Console

Network Pruning On Imagenet

Metrics

Accuracy

Results

Performance results of various models on this benchmark

Paper Title
ResNet50-2.3 GFLOPs78.79Pruning Filters for Efficient ConvNets
ResNet50-1.5 GFLOPs78.07Pruning Filters for Efficient ConvNets
ResNet50 2.5 GFLOPS78.0Knapsack Pruning with Inner Distillation
RegX-1.6G77.97Group Fisher Pruning for Practical Network Compression
ResNet50 2.0 GFLOPS77.70Knapsack Pruning with Inner Distillation
ResNet50-3G FLOPs77.1EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning
ResNet50-2G FLOPs76.4EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning
ResNet50-1G FLOPs76.376Pruning Filters for Efficient ConvNets
TAS-pruned ResNet-5076.20Network Pruning via Transformable Architecture Search
ResNet5075.59Network Pruning That Matters: A Case Study on Retraining Variants
ResNet50-1G FLOPs74.2EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning
ResNet50-1G FLOPs74.2EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning
MobileNetV273.42Group Fisher Pruning for Practical Network Compression
ResNet5073.14AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks
MobileNetV1-50% FLOPs70.7EagleEye: 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