Picasso: A Modular Framework for Visualizing the Learning Process of Neural Network Image Classifiers
arXiv:1705.05627 · doi:10.5334/jors.178
Abstract
Picasso is a free open-source (Eclipse Public License) web application written in Python for rendering standard visualizations useful for analyzing convolutional neural networks. Picasso ships with occlusion maps and saliency maps, two visualizations which help reveal issues that evaluation metrics like loss and accuracy might hide: for example, learning a proxy classification task. Picasso works with the Tensorflow deep learning framework, and Keras (when the model can be loaded into the Tensorflow backend). Picasso can be used with minimal configuration by deep learning researchers and engineers alike across various neural network architectures. Adding new visualizations is simple: the user can specify their visualization code and HTML template separately from the application code.
arXiv comment9 pages, submission to the Journal of Open Research Software, github.com/merantix/picasso
References in corpus (6)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Understanding Neural Networks Through Deep Visualization
- Understanding deep learning requires rethinking generalization
- Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
- Mask R-CNN
- Fully Convolutional Instance-aware Semantic Segmentation