Library release: visualize saliency map of deep neural network

Japanese is available at Qiita. From left: 1. Classification saliency map visualization of VGG16, CNN model. 2. iris dataset feature importance calculation of MLP model. 3. Water solubility contribution visualization of Graph convolutional network model. Abstract Have you ever thought “Deep neural network is highly complicated black box, no one ever able to see what […]

Continue reading →