search

KaiyangZhou / pytorch-center-loss

Pytorch implementation of Center Loss
MIT License
965 stars 218 forks source link

High dimension feature embedding visualization #15

Closed hfutzzw closed 4 years ago

hfutzzw commented 4 years ago

Hi, Kaiyang. The feature embedding is 2-dim in this repository and it is straightforward to visualize. But if the feature is in a high-dimension space (e.g 2048, ResNet50 GAP feature). How I visualize it in 2-d feature space, should I utilize the approaches such as PCA or TSNE ?

caijie0620 commented 4 years ago

Yes, you can use tsne to visualize high-dimension data.