Keras implementation of class activation mapping
-
Updated
Aug 5, 2017 - Python
Keras implementation of class activation mapping
Neat (Neural Attention) Vision, is a visualization tool for the attention mechanisms of deep-learning models for Natural Language Processing (NLP) tasks. (framework-agnostic)
Training and evaluating state-of-the-art deep learning CNN architectures for plant disease classification task.
🏔️ Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations
Interesting resources related to Explainable Artificial Intelligence, Interpretable Machine Learning, Interactive Machine Learning, Human in Loop and Visual Analytics.
Attribution (or visual explanation) methods for understanding video classification networks. Demo codes for WACV2021 paper: Towards Visually Explaining Video Understanding Networks with Perturbation.
Notebooks for Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations
My Notes on Deep Learning 💫
Visualize the convergence of complex roots with different optimizers.
📉 Visualize your Deep Learning training in static graphics
Data for Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations
Pure Swift TensorBoard plugin for DL4S
Major: Computer Graphics
An abstract deep learning training framework.
FitsBook Python Library. Tool for generating real-time machine learning training statistics and storing model histories. Direct integration with Keras Framework.
Keras implementation of class activation mapping
MNIST classifier with a graphical user interface and a canvas for drawing the digits, doing classifying in real time
A simple simple version of tensorboard implemented by d3.js
Fitsbook React WebApp. Tool for generating real-time machine learning training statistics and storing model histories. Direct integration with Keras.
Add a description, image, and links to the deep-learning-visualization topic page so that developers can more easily learn about it.
To associate your repository with the deep-learning-visualization topic, visit your repo's landing page and select "manage topics."