Experiments using the FastAI framework for image classification.
The goal of this project was to:
- understand transfer learning
- experiment with data augmentation
- evaluate model performance on a custom dataset
- Python 3.10
- fastai
- PyTorch
Brief description (source, size, type).
- Pretrained ResNet
- Fine-tuning
- Data augmentation
Accuracy: 0,87 Validation loss: 0,42
conda env create -f environment.yml jupyter notebook