search

YyzHarry / imbalanced-semi-self

[NeurIPS 2020] Semi-Supervision (Unlabeled Data) & Self-Supervision Improve Class-Imbalanced / Long-Tailed Learning
https://arxiv.org/abs/2006.07529
MIT License
735 stars 115 forks source link

How to get the image in the readme #23

Closed 87nohigher closed 2 years ago

87nohigher commented 2 years ago

Could you give some hint how to get the image stored in the directory of assets? I want to get that type of image on my own dataset. Thanks tsne_self

YyzHarry commented 2 years ago

Hi - As stated in our paper, the figure is generated using t-SNE projection of the learnt representations. You can first save the features and then run t-SNE on them. We used the tsne function in the sklearn library for implementation.

87nohigher commented 2 years ago

Thanks for your reply. Could you release the code of the implementation? Thanks a lot

YyzHarry commented 2 years ago

Unfortunately I didn't save the visualization as a single file, but it should be simple and straightforward to implement: save the features first, and then run t-SNE on them.

87nohigher commented 2 years ago

Thanks, I have implemented it successfully.