https://github.com/crepopcorn/cat-vs-dog-vit-project

https://github.com/crepopcorn/cat-vs-dog-vit-project

dog-vs-cat image-classification machine-learning python transformer vit

Last synced: 1 day ago
JSON representation

• Host: GitHub
• URL: https://github.com/crepopcorn/cat-vs-dog-vit-project
• Owner: Crepopcorn
• Created: 2023-11-01T05:49:52.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2023-11-12T22:25:20.000Z (almost 2 years ago)
• Last Synced: 2025-01-16T06:58:12.188Z (9 months ago)
• Topics: dog-vs-cat, image-classification, machine-learning, python, transformer, vit
• Language: Jupyter Notebook
• Homepage:
• Size: 1.61 MB
• Stars: 2
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# cat-vs-dog-vit-project

Using the trained Vision Transformer (ViT) Model, get the following output results using training dataset:

![image](https://github.com/Crepopcorn/cat-vs-dog-vit-project/assets/112138670/c2b18d7c-58e6-44b4-b724-c4a2b5550425)

Thus, we can conclude that:

![image](https://github.com/Crepopcorn/cat-vs-dog-vit-project/assets/112138670/1897fc9e-a833-4f40-a16d-e3bfc0a9964d)

In addition, the trained model validation accuracy and loss can be shown as below:

![image](https://github.com/Crepopcorn/cat-vs-dog-vit-project/assets/112138670/b9f8e911-bf18-40b8-be84-25535d911144)