Título: QUALITATIVE ANALYSIS OF DEEP LEARNING FRAMEWORKS
Autor: Matheus Gutoski, Leandro Takeshi Hattori, Nelson Marcelo Romero Aquino, Helen Cristina Mattos Senefonte, Manassés Ribeiro, André Eugênio Lazzaretti, Heitor Silvério Lopes
Resumo: Deep learning methods are becoming more popular for complex pattern recognition applications. As result, many frameworks have appeared aiming to facilitate the development of such applications. However, choosing a suitable framework may not be an easy task for new users. In this paper, a qualitative evaluation of four of the most popular Deep Learning frameworks is provided, including: Caffe, Torch, Lasagne and TensorFlow. A printed character recognition task was used as case study, and a Convolutional Neural Network was implemented for this purpose. The analysis focus on issues that are important for the development process and encompasses nine qualitative dimensions, showing the strengths and weaknesses of each framework. It is expected that this analysis can be useful for guiding new users in the area.
Palavras-chave: Deep Learning, Caffe, Torch, Lasagne, TensorFlow, Convolutional Neural Networks.
Código DOI: 10.21528/LNLM-vol15-no1-art3
Artigo em PDF: vol15-no1-art3.pdf
Arquivo BibTex: vol15-no1-art3.bib