Year: 2018
Type: preprint
Abstract: This study provides benchmarks for different implementations of LSTM units between the deep learning frameworks PyTorch, TensorFlow, Lasagne and Keras. The comparison includes cuDNN LSTMs, fused LSTM variants and less optimized, but more flexible LSTM implementations. The benchmarks reflect two typical scenarios for automatic speech recognition, notably continuous speech recognition and isolated digit recognition. These scenarios cover input sequences of fixed and variable length as well as the loss functions CTC and cross entropy. Additionally, a comparison between four different PyTorch versions is included. The code is available online https://github.com/stefbraun/rnn_benchmarks.
Source: arXiv (Cornell University)
Author: Braun, Stefan
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2806181750