README.md

metadata

title: flowers-classification
sdk: docker
emoji: 🌍
colorFrom: gray
colorTo: green

About

Image classification model trained using PyTorch Lightning framework and shared on Hugging Face with the use of gradio and Docker.

• Architecture: simple Deep Convolutional Neural Network (DeepCNN)
• Dataset: 102 Category Flower Dataset
• Experiments: all experiments are logged to the WandB project which can be found here

Tech stack

• PyTorch - neural networks architectures and datasets classes
• PyTorch Lightning - model training and evaluation
• plotly - visualizations
• WandB - metrics, visualizations and model logging
• torchmetrics - metrics calculation
• gradio - application used to show how model works in real world
• Docker - containerize application to allow for Hugging Face deploy

Commands

1. Train the model:

make train_model

2. Run docker with gradio app:

docker build -t flowers .
docker run -it -p 7860:7860 --name flowers_app flowers