Comparative Performance Evaluation of TensorFlow and PyTorch for Handwritten Digit and Image Classification Using MNIST, EMNIST, and CIFAR-10 Datasets

DOI

10.2991/978-94-6463-716-8_9How to use a DOI?

Keywords

Handwritten Digit Recognition; Image Classification; Training Time; Detection Time; Resource Utilization; Model Size; PyTorch; TensorFlow

Abstract

In this paper we provide results of performance comparison of handwritten digit recognition and complex image classification. We used TensorFlow and PyTorch digital libraries to obtain results. The datasets used were CIFAR-10, MNIST, and EMNIST. The parameters like training time, detection time, resource usage, accuracy, and model size were considered. A standard neural network was trained using a training dataset and results were validated using validation dataset. The experimental results show varying efficiency, utilization, and model performance.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Aayushya Lakkadwala
AU  - Prashant Lakkadwala
PY  - 2025
DA  - 2025/05/26
TI  - Comparative Performance Evaluation of TensorFlow and PyTorch for Handwritten Digit and Image Classification Using MNIST, EMNIST, and CIFAR-10 Datasets
BT  - Proceedings of the International Conference on Recent Advancements and Modernisations in Sustainable Intelligent Technologies and Applications (RAMSITA 2025)
PB  - Atlantis Press
SP  - 100
EP  - 111
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-716-8_9
DO  - 10.2991/978-94-6463-716-8_9
ID  - Lakkadwala2025
ER  -