https://github.com/bayyy7/efficientnetb4_herbleave

Herb Leave Classification using EfficientNetB4
https://github.com/bayyy7/efficientnetb4_herbleave

Last synced: 3 days ago
JSON representation

Herb Leave Classification using EfficientNetB4

• Host: GitHub
• URL: https://github.com/bayyy7/efficientnetb4_herbleave
• Owner: bayyy7
• License: mit
• Created: 2023-05-08T14:35:33.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2023-05-08T18:35:34.000Z (almost 2 years ago)
• Last Synced: 2024-12-19T07:13:08.004Z (about 2 months ago)
• Language: Jupyter Notebook
• Homepage:
• Size: 761 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Image Classification Using Transfer Learning

Image Classification using Pre-Trained model EfficientNetB4 


Only sing 2 class from dataset (Pepaya & Nangka)


Testing using M1 GPU with 5 epoch 


You can run more than 10 epoch to get better result.


### Using EfficientNetB4:


- Accuracy : 99.71%


- Loss : 08.21%


# More Pre-Trained Model

You can learn more pre-trained from here 


https://keras.io/api/applications/ 


# Data

Get data using this link https://data.mendeley.com/datasets/s82j8dh4rr

# Cite 

Minarno, Agus Eko; Wicaksono, Galih Wasis; Azhar, Yufis; Hasanuddin, Muhammad Yusril (2022), “Indonesian Herb Leaf Dataset 3500”, Mendeley Data, V1, doi: 10.17632/s82j8dh4rr.1