{"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/fast-generation-for-convolutional","title":"Fast Generation for Convolutional Autoregressive Models","arxiv_id":"1704.06001","date":"2017-04-20","proceeding":null,"authors":["Prajit Ramachandran","Tom Le Paine","Pooya Khorrami","Mohammad Babaeizadeh","Shiyu Chang","Yang Zhang","Mark A. Hasegawa-Johnson","Roy H. Campbell","Thomas S. Huang"],"abstract":"Convolutional autoregressive models have recently demonstrated\nstate-of-the-art performance on a number of generation tasks. While fast,\nparallel training methods have been crucial for their success, generation is\ntypically implemented in a na\\\"{i}ve fashion where redundant computations are\nunnecessarily repeated. This results in slow generation, making such models\ninfeasible for production environments. In this work, we describe a method to\nspeed up generation in convolutional autoregressive models. The key idea is to\ncache hidden states to avoid redundant computation. We apply our fast\ngeneration method to the Wavenet and PixelCNN++ models and achieve up to\n$21\\times$ and $183\\times$ speedups respectively.","url_abs":"http://arxiv.org/abs/1704.06001v1","url_pdf":"http://arxiv.org/pdf/1704.06001v1.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":"fast-generation-for-convolutional","repo_url":"https://github.com/PrajitR/fast-pixel-cnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[],"methods":[{"method_slug":"dilated-causal-convolution","method_name":"Dilated Causal Convolution"},{"method_slug":"mixture-of-logistic-distributions","method_name":"Mixture of Logistic Distributions"},{"method_slug":"wavenet","method_name":"WaveNet"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.06001","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}