search

cmhungsteve / TA3N

[ICCV 2019 (Oral)] Temporal Attentive Alignment for Large-Scale Video Domain Adaptation (PyTorch)
https://arxiv.org/abs/1907.12743
MIT License
259 stars 41 forks source link

T-SNE visualization #14

Closed lerndeep closed 4 years ago

lerndeep commented 4 years ago

I want to visualized data after a training network. could you provide an idea of how can I visualize source and target data after training for comparison of data alignment way? I read your paper you are using T-SNE for visualization but I have no idea how can I use T-SNE after training finished. I prepared T-SNE before training source and target data but after training, I have a problem with visualization.

cmhungsteve commented 4 years ago

I use tensorboard-X. You just need to feed data and domain labels to the embedding API of tensorboard, then you can generate the t-SNE visualization.