{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/picasso-a-modular-framework-for-visualizing","title":"Picasso: A Modular Framework for Visualizing the Learning Process of Neural Network Image Classifiers","arxiv_id":"1705.05627","date":"2017-05-16","proceeding":null,"authors":["Ryan Henderson","Rasmus Rothe"],"abstract":"Picasso is a free open-source (Eclipse Public License) web application\nwritten in Python for rendering standard visualizations useful for analyzing\nconvolutional neural networks. Picasso ships with occlusion maps and saliency\nmaps, two visualizations which help reveal issues that evaluation metrics like\nloss and accuracy might hide: for example, learning a proxy classification\ntask. Picasso works with the Tensorflow deep learning framework, and Keras\n(when the model can be loaded into the Tensorflow backend). Picasso can be used\nwith minimal configuration by deep learning researchers and engineers alike\nacross various neural network architectures. Adding new visualizations is\nsimple: the user can specify their visualization code and HTML template\nseparately from the application code.","url_abs":"http://arxiv.org/abs/1705.05627v3","url_pdf":"http://arxiv.org/pdf/1705.05627v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"picasso-a-modular-framework-for-visualizing","repo_url":"https://github.com/merantix/picasso","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.05627","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}