Carvana-Image-Segmentation-Using-UNET

Masking of Car Images using PyTorch and deployed using Heroku

The model architecture used is UNET which is trained using PyTorch, with the final model being converted to ONNX format and deployed using Heroku.

Dataset 📂

Dataset used from Kaggle Carvana Image Masking Challenge which contains a large number of car images (as .jpg files). Each car has exactly 16 images, each one taken at different angles.

Notebook 📒

View the notebook here

Deployment 🚀

The model has been converted to ONNX format and deployed using Gradio & hosted on Heroku: Car Image Masking

Predictions 🔍

Predictions on unseen test data:

1)

2)