https://github.com/mohamedmetwalli5/imageclassification-tensorflow

Image Classification Using TensorFlow
https://github.com/mohamedmetwalli5/imageclassification-tensorflow

cnn tensorflow

Last synced: 3 months ago
JSON representation

Image Classification Using TensorFlow

• Host: GitHub
• URL: https://github.com/mohamedmetwalli5/imageclassification-tensorflow
• Owner: MohamedMetwalli5
• Created: 2022-04-29T03:28:21.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2022-04-29T06:41:46.000Z (over 3 years ago)
• Last Synced: 2025-07-03T02:04:05.231Z (3 months ago)
• Topics: cnn, tensorflow
• Language: Jupyter Notebook
• Homepage:
• Size: 32.2 KB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
![License](https://img.shields.io/badge/License-GPL–3.0%20-violet.svg)

![Language](https://img.shields.io/badge/language-Python%20-blue.svg)

# ImageClassification-TensorFlow

## About The CNN

  * Kernel Size = 3*3

  * Activation Function = Rectified Linear Units (ReLU)

  * ![image](https://user-images.githubusercontent.com/58489322/165895959-7935335e-1ac5-4f43-a480-f6324783289d.png)

## The DataSet

The CIFAR-10 dataset

The CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images.

The dataset is divided into five training batches and one test batch, each with 10000 images. The test batch contains exactly 1000 randomly-selected images from each class. The training batches contain the remaining images in random order, but some training batches may contain more images from one class than another. Between them, the training batches contain exactly 5000 images from each class.

![image](https://user-images.githubusercontent.com/58489322/165889333-f5e4cdd6-5ad6-4d89-b81c-ab5e607f2f69.png)