English | 中文

Create conda environment

conda env create -f ./env_gcnet.yml  

conda activate gcnet

Pretrained models

• GraphConvNet

Model	Params (M)	FLOPs (B)	Top-1	BaiduDisk URL
GraphConvNet-Ti	7.7	1.3	77.1	BaiduDisk URL
GraphConvNet-S	24.5	4.9	82.0	BaiduDisk URL

• Pyramid GraphConvNet

Model	Params (M)	FLOPs (B)	Top-1	BaiduDisk URL
Pyramid GraphConvNet-Ti	11.4	1.8	80.5	BaiduDisk URL
Pyramid GraphConvNet-S	29.2	4.9	82.4	BaiduDisk URL

Train & Evaluation

Change parameters in run.sh and then run

source run.sh

Visualization

The visualization code only available to GraphConvNet and ViG

1. Create a folder named 'ckpt' in './viz_nodes' and download the checkpoints of GraphConvNet-Ti or GraphConvNet-S and put them in './viz_nodes/ckpt'
2. Open viz_demo.ipnb, and set arguments (arch, etc.)
3. Run cells

⚠️⚠️⚠️ If you want to visualize ViG, please download the checkpoints I provide here, since I reorganized ViG code and transformed the official checkpoints' state_dict to suit my code.

Demo:

The first row: gradcam heatmaps of GraphConvNet-Ti in 4th, 8th, 12th layers.
The second row: the patch(node) that has the max gradcam value(most discriminative) and its corresponding neighbors in different layers.
The third row: add edges, the pentagram is the most discriminative node.(you can draw edges using tools such as PowerPoint, OmniGraffle..)

CAM Images:

4th Layer	8th Layer	12th Layer

Center & Neighbors:

4th Layer	8th Layer	12th Layer

Graph Visualization:

4th Layer	8th Layer	12th Layer

Acknowledgement

This repo partially uses code from vig