Improved Method of ResNet50 Image Classification Based on Transfer Learning

convolutional layer	output layer	ResNet50
Conv-1	112×112	7×7, 64, S=2 3×3 maxpool, S=2
Conv2-x	56×56	$[\begin{matrix} 1 \times 1 & 64 \\ 3 \times 3 & 64 \\ 1 \times 1 & 256 \end{matrix}] * 3$
Conv3-x	28×28	$[\begin{array}{l} 1 \times 1 & 128 \\ 3 \times 3 & 128 \\ 1 \times 1 & 512 \end{array}] * 4$
Conv4-x	14×14	$[\begin{matrix} 1 \times 1 & 256 \\ 3 \times 3 & 256 \\ 1 \times 1 & 1024 \end{matrix}] * 6$
Conv5-x	7×7	$[\begin{matrix} 1 \times 1 & 512 \\ 3 \times 3 & 512 \\ 1 \times 1 & 2048 \end{matrix}] * 3$
1×1	Average_pool,1000-dfc, Soft_max
Flops		3.8×10⁹

Language: English

Page range: 1 - 9

Published on: Jun 16, 2025

Published by: Xi’an Technological University

In partnership with: Paradigm Publishing Services

Publication frequency: 4 issues per year

Keywords:

Related subjects:

© 2025 Tao Shi, Jun Yu, Zhiyi Hu, Kuncai Jiang, published by Xi’an Technological University
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Figures & Tables