Skip to main content
. 2017 Jun 1;12(6):e0177544. doi: 10.1371/journal.pone.0177544

Fig 5. 2D projection of the training patches and their activations on different layers of the CNN using t-SNE [29].

Fig 5

A training patches; B last convolutional layer; C second fully-connected layer. Diamond shapes represent test images.