Dive into the fundamentals of text recognition through a comprehensive series of labs from the Full Stack Deep Learning March 2019 bootcamp. Explore project structure, setup instructions, and key components including API folders, serverless files, and data organization. Learn about predictor files, data sets, models, and weights while gaining hands-on experience with training code, deployment workflows, and model management. Discover the intricacies of character models, running training sessions, and conducting tests. Gain valuable insights into model architecture and work with tools like Jupiter Lab and Jupiter Notebook. Utilize the MiniNIST and EMS data sets to practice loading and manipulating data, and delve into basic network and model code implementation.
Introduction to the Text Recognizer Project - Full Stack Deep Learning - March 2019
Overview
Syllabus
Introduction
Project Overview
Labs Outline
Github
Setup instructions
API folder
Serverless file
Data folder
Evaluation folder
ipython notebooks folder
Predictor files
Data sets
Models
Weights
Training Code
Setup
Deployment
Workflow
Structure
Lab 2 Setup
Weights Biases
Lab Structure
Jupiter Lab
Jupiter Notebook
MiniNIST
EMS Data Set
Load Data Set
Data Set Classes
Basic Network Code
Basic Model Code
Model Management
Character Model
Running Training
Running Tests
Model Architecture
Taught by
The Full Stack
