gnnrl pipeline
Project description
GNN-RL-Model-Compression
GNN-RL Compression: Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning
Dependencies
Current code base is tested under following environment:
- Python 3.8
- PyTorch 1.8.0 (cuda 11.1)
- torchvision 0.7.0
- torch-geometric 1.6.1
Results on ImageNet
Models | FLOPs ratio | Top1 Acc. (%) | Acc. | Dataset |
---|---|---|---|---|
MobileNet-v1 | 40% FLOPs | 69.50 | -1.40 | ImageNet |
MobileNet-v1 | 70% FLOPs | 70.70 | -0.20 | ImageNet |
MobileNet-v2 | 58% FLOPs | 70.04 | -1.83 | ImageNet |
VGG-16 | 20% FLOPs | 70.992 | +0.49 | ImageNet |
ResNet-50 | 47% FLOPs | 74.28 | -1.82 | ImageNet |
ResNet-18 | 50% FLOPs | 68.66 | -1.10 | ImageNet |
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
gnnrl-1.0.6.tar.gz
(104.2 MB
view hashes)
Built Distribution
gnnrl-1.0.6-py3-none-any.whl
(104.3 MB
view hashes)