Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

CodeSignal

JAX in Action: Building an Image Classifier

via CodeSignal

Go to class Write review

Overview

Apply your JAX, Flax, and Optax skills to a practical project: building an image classification pipeline. This course covers setting up a multi-file project, loading and preprocessing image data (e.g., MNIST), defining a Convolutional Neural Network (CNN) with Flax, and implementing robust training and evaluation loops.

Syllabus

  • Unit 1: Project Kickstart: Data Loading & Preprocessing
    • Preparing Images for Neural Networks
    • Preparing Images for Deep Learning
    • Supercharging Your Data Pipeline
    • Preparing Data for Training
    • Debug Your Data Pipeline
  • Unit 2: Crafting a CNN with Flax: Conv and Pooling Layers
    • Building Your First Convolutional Block
    • From Features to Predictions
    • Debug Your CNN Model
    • Building Deeper Neural Networks
  • Unit 3: Training & Evaluation Steps: The Core Engine
    • Teaching Your Model Right from Wrong
    • Building Model Assessment Tools
    • Complete the Training Step Function
    • Connect Your Training Pipeline
  • Unit 4: Full Pipeline: Training and Evaluating the CNN
    • Build Your Training Foundation
    • Complete Metric Aggregation Logic
    • Completing the Training Loop
    • Complete the Evaluation Loop

Reviews

Start your review of JAX in Action: Building an Image Classifier

Go to class

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free
Someone learning on their laptop while sitting on the floor.