GSM
GSM copied to clipboard
t-sne
In the paper, which layer of features is used in Figure 5 to make t-sne
The feature obtained after spatial average pooling in BNInception is used for the t-SNE.
Is it the feature obtained from here (https://github.com/swathikirans/GSM/blob/master/models.py#L194)?
Yes, you are right.
Thank you for your reply. But the shape I extracted from base_out is (8, 2048). How to make the spatial average pooling
The output from the backbone (8X2048) is temporal average pooled to obtain a vector (2048) and is used for t-SNE visualization.