rizveehasan19/end-to-end-image-classification

end-to-end-image-classification

This is an image classification project that includes data collection, cleaning, model training, deployment and API integration.
This model can classify 10 different types of flowers
The types are following:

1. aster
2. daffodil
3. dahlia
4. daisy
5. dandelion
6. iris
7. orchid
8. rose
9. sunflower
10. tulip

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/data_prep.ipynb

Training and Data Cleaning

Training: Fine-tuned a resnet34 model for 5 epochs (2 times) and got upto ~86% accuracy.
Data Cleaning: I cleaned and updated data using fastai ImageClassifierCleaner. I cleaned the data each time after training or fine tuning, 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 the app folder and in the corresponding Space.

API integration with GitHub Pages

The deployed model API is integrated in GitHub Pages Website. Implementation and other details can be found in docs folder.