NAME OF PROJECT
Operation Blossom
PROJECT DESCRIPTION
Vision Transformers (ViT) is an up and coming technology with news that it will be replacing Convolutional Neural Networks (CNN). We want to demystify this claim by experimenting ourselves with a flower images dataset. The task will be to identify the flower in an image. We will build a Streamlit app that runs both a CNN and ViT and compare the accuracy and duration time of Convolutional Neural Networks and Vision Transformers. The model predictions will be displayed along with the training and testing results of both CNN and ViT.
GRANT DELIVERABLES
- Run a CNN and tune the model
- Run and tune a ViT model
- Build a Streamlit app allowing users to upload images
- Build a pipeline that takes users images and makes predictions
- Display training process of both CNN and ViT
SQUAD
Ren W
- Twitter: https://twitter.com/renweview
- Discord: tea first#5268
Tariq R
- Twitter: @taraqur
- Discord: the_proton_crusher#8317
- ETH: 0x32aE0C5b4e34340e4e1550a92d0B6206c68663A3