https://github.com/jarif87/fruit-recognizer
Built a fastai fruit recognition model for precise and efficient identification using advanced deep learning
https://github.com/jarif87/fruit-recognizer
computer-vision deep-learning machine-learning prediction python
Last synced: 2 months ago
JSON representation
Built a fastai fruit recognition model for precise and efficient identification using advanced deep learning
- Host: GitHub
- URL: https://github.com/jarif87/fruit-recognizer
- Owner: jarif87
- License: mit
- Created: 2023-12-19T09:58:24.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-04-17T03:12:29.000Z (about 2 years ago)
- Last Synced: 2025-01-25T21:09:43.525Z (over 1 year ago)
- Topics: computer-vision, deep-learning, machine-learning, prediction, python
- Language: Jupyter Notebook
- Homepage: https://huggingface.co/spaces/jarif/Fruit_Recognizer_Part_2
- Size: 5.79 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Fruit-Recognizer
An image classification model from data collection, cleaning, model training, deployment and API integration.
The model can classify 20 different types of fruits.
The types are following:
* Apple
* Grape
* Kiwi
* Orange
* Pineapple
* Papaya
* Watermelon
* Lemon
* Avocado
* Raspberry
* Lychee
* Pear
* Carambola
* Mango
* Banana
* Cherry
* Strawberry
* Fig
* Blueberry
* Apricot
# Dataset Preparation
**Data Collection:** Downloaded from DuckDuckGo using term name
**DataLoader:** Used fastai DataBlock API to set up the DataLoader.
**Data Augmentation:** fastai provides default data augmentation which operates in GPU.
Details can be found in `Notebooks/Fruit_Recognizer.ipynb`
# Training and Data Cleaning
**Training:** Fine-tuned a resnet50 model for 5 epochs (3 times) and got upto ~84% accuracy.
**Data Cleaning:** This part took the highest time. Since I collected data from browser, there were many noises. Also, there were images that contained. I cleaned and updated data using fastai ImageClassifierCleaner. I cleaned the data each time after training or finetuning, except for the last time which was the final iteration of the model.
# Model Deployment
I deployed to model to HuggingFace Spaces Gradio App. The implementation can be found in `Deployment` folder or [here](https://huggingface.co/spaces/jarif/Fruit_Recognizer_Part_2).
# API integration with GitHub Pages
The deployed model API is integrated [here](https://jarif87.github.io/Fruit-Recognizer/) in GitHub Pages Website. Implementation and other details can be found in `Docs` folder.