Analysis of Deep Learning Libraries: Keras, PyTorch, and MXnet
Document Type
Conference Proceeding
Publication Date
6-30-2022
Publication Title
IEEE/ACIS 20th International Conference on Software Engineering Research, Management and Applications (SERA) Proceedings
DOI
10.1109/SERA54885.2022.9806734
Abstract
- As many artificial neural libraries are developing the deep learning algorithm and implementing it became accessible to anyone. This study points out the disparity of performance in deep learning models such as convolutional neural networks (CNN) when implemented with different artificial neural libraries. Libraries such as Keras, Pytorch, and MXnet was utilized for each three CNN model then binary image classification was done based on the Dogs vs. Cats dataset from Kaggle. With using 75% of the dataset as the training set and the rest of 25% as a testing set, and as a result, each CNN model gave a different F1 score value and accuracy.
Recommended Citation
Kim, Seongsoo, Hayden Wimmer, Jongyeop Kim.
2022.
"Analysis of Deep Learning Libraries: Keras, PyTorch, and MXnet."
IEEE/ACIS 20th International Conference on Software Engineering Research, Management and Applications (SERA) Proceedings: 54-62: IEEE Xplore.
doi: 10.1109/SERA54885.2022.9806734
https://digitalcommons.georgiasouthern.edu/information-tech-facpubs/175
Comments
Georgia Southern University faculty member, Hayden Wimmer and Jongyeop Kim co-authored Analysis of Deep Learning Libraries: Keras, PyTorch, and MXnet.