Phase 2: Object Detection & Segmentation · ~75 minutes · Python

Real-Time Vision — Edge Deployment

Edge inference is the discipline of getting a 90-accuracy model to run at 30 fps on a device with 2 GB of RAM. Every percentage point of accuracy is traded against milliseconds of latency.

What you will learn

Measure inference latency, peak memory, and throughput for any PyTorch model, and read the FLOPs / params / latency trade-off
Quantise a vision model to INT8 using PyTorch's post-training quantisation and verify accuracy loss < 1%
Export to ONNX and compile with ONNX Runtime or TensorRT; name the three most common export failures and their fixes
Explain when to pick MobileNetV3, EfficientNet-Lite, ConvNeXt-Tiny, or MobileViT for an edge constraint

Introduction

Type: Learn + Build
Languages: Python
Prerequisites: the Transformers & LLMs from Scratch course, Image Classification
Time: ~75 minutes

Objective

Learning objectives

Measure inference latency, peak memory, and throughput for any PyTorch model, and read the FLOPs / params / latency trade-off
Quantise a vision model to INT8 using PyTorch's post-training quantisation and verify accuracy loss < 1%
Export to ONNX and compile with ONNX Runtime or TensorRT; name the three most common export failures and their fixes
Explain when to pick MobileNetV3, EfficientNet-Lite, ConvNeXt-Tiny, or MobileViT for an edge constraint

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers The Problem, The Concept, Build, Check Yourself, Key Terms & Next — plus a hands-on lab, quiz, and project artifact.

Create a free account — the opening phases of 29 of 35 courses are free, no credit card.