{"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/lstm-benchmarks-for-deep-learning-frameworks","title":"LSTM Benchmarks for Deep Learning Frameworks","arxiv_id":"1806.01818","date":"2018-06-05","proceeding":null,"authors":["Stefan Braun"],"abstract":"This study provides benchmarks for different implementations of LSTM units\nbetween the deep learning frameworks PyTorch, TensorFlow, Lasagne and Keras.\nThe comparison includes cuDNN LSTMs, fused LSTM variants and less optimized,\nbut more flexible LSTM implementations. The benchmarks reflect two typical\nscenarios for automatic speech recognition, notably continuous speech\nrecognition and isolated digit recognition. These scenarios cover input\nsequences of fixed and variable length as well as the loss functions CTC and\ncross entropy. Additionally, a comparison between four different PyTorch\nversions is included. The code is available online\nhttps://github.com/stefbraun/rnn_benchmarks.","url_abs":"http://arxiv.org/abs/1806.01818v1","url_pdf":"http://arxiv.org/pdf/1806.01818v1.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":"lstm-benchmarks-for-deep-learning-frameworks","repo_url":"https://github.com/stefbraun/rnn_benchmarks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}