search

ranahanocka / MeshCNN

Convolutional Neural Network for 3D meshes in PyTorch
MIT License
1.56k stars 314 forks source link

Can MeshCNN output an activation map? #57

Open sunhuaiqiang opened 4 years ago

sunhuaiqiang commented 4 years ago

or something like that to display which parts contribute to classification.

ranahanocka commented 4 years ago

Hi @sunhuaiqiang ,

The intermediate mesh pooling results are a nice way to visualize which parts didn't contribute to classification (they are exported during the test pass , if the --export_folder flag is used, like in the examples provided -- e.g., here). Otherwise, you would have to implement some visualization approach, like Grad-CAM.