Picasso: A Modular Framework for Visualizing the Learning Process of Neural Network Image Classifiers

  title={Picasso: A Modular Framework for Visualizing the Learning Process of Neural Network Image Classifiers},
  author={R. Henderson and R. Rothe},
  journal={Journal of open research software},
  • R. Henderson, R. Rothe
  • Published 2017
  • Computer Science
  • Journal of open research software
  • 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… CONTINUE READING
    4 Citations
    Seq2seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models
    • 89
    • PDF
    End-to-end Learning for Autonomous Navigation for Agricultural Robots
    • PDF
    Classifying Alzheimer’s from fMRI Data using Convolutional Networks
    • Nikhil Sardana
    • 2018
    • PDF
    Deep Learning for Self-Driving Cars: Chances and Challenges
    • Q. Rao, Jelena Frtunikj
    • Computer Science
    • 2018 IEEE/ACM 1st International Workshop on Software Engineering for AI in Autonomous Systems (SEFAIAS)
    • 2018
    • 44
    • Highly Influenced


    Visualizing and Understanding Convolutional Networks
    • 9,097
    • PDF
    Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
    • 3,077
    • PDF
    Understanding Neural Networks Through Deep Visualization
    • 1,191
    • PDF
    Learning Deep Features for Discriminative Localization
    • 3,066
    • PDF
    Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
    • 2,240
    • PDF
    Very Deep Convolutional Networks for Large-Scale Image Recognition
    • 44,924
    • Highly Influential
    • PDF
    Understanding deep learning requires rethinking generalization
    • 2,419
    • PDF
    Fully Convolutional Instance-Aware Semantic Segmentation
    • 506
    • PDF
    TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
    • 8,072
    • PDF