Project developed during lab sessions of the Full Stack Deep Learning Bootcamp.
- Handwriting recognition system from scratch, and deploy it as a web service.
- Uses Keras, but designed to be modular, hackable, and scalable
- Provides code for training models in parallel and store evaluation in Weights & Biases
- We will set up continuous integration system for our codebase, which will check functionality of code and evaluate the model about to be deployed.
- We will package up the prediction system as a REST API, deployable as a Docker container.
- We will deploy the prediction system as a serverless function to Amazon Lambda.
- Lastly, we will set up monitoring that alerts us when the incoming data distribution changes.
- Started with base model MLP/CNN
- Run LeNet model on subsampling dataset
- Train CNN for reading lines
- Train LSTM on Emnist
- TODO : Train Encoder - Decoder architecture with attention
- Download IAM handwriting dataset
- Use weight and bias for metrics
- Run multiple experiments in parallel with hyper param sweeps
- Train data augmentation
- Ensemble 2 models
- Test
- Deploy model
- First session (90 min)
- Second session (60 min)
- Third session (90 min)
- Fourth session (75 min)