TensorFlow Developer Specialization · CNNs in TensorFlow

Horse or Human Classifier with Transfer Learning

A transfer-learning classifier that uses a frozen InceptionV3 network and a custom head for horse-vs-human image classification.

InceptionV3Transfer learningFrozen feature extractormixed7 layerBinary classification

GitHub

What this project is about

This project uses InceptionV3 as a frozen visual backbone and trains a small classifier on top. It demonstrates why transfer learning is powerful when a dataset is limited.

Implementation focus

The key learning was to reuse learned visual features, select an intermediate layer, and train only the task-specific head before considering fine-tuning.

Key results and artifacts

Training images: 1,027; validation images: 256
Training stopped at accuracy 0.9990
Validation accuracy around 91.96%
Test accuracy: 87.5%

What I learned

This milestone showed when to reuse strong pretrained convolutional features instead of training every layer from scratch.

Milestone deep dive

What this project proves in my learning path.

A transfer-learning classifier that uses a frozen InceptionV3 network and a custom head for horse-vs-human image classification. The milestone is included because it shows a complete learning unit: a problem, a data representation, an implementation path, measurable outputs, and a lesson that later connects to larger AI systems.

Input layercourse dataset, features, labels, or raw input artifacts

Model layerimplemented algorithm or neural network pipeline

Evaluation layertests, metrics, plots, or qualitative output

Artifact layermetrics, plots, predictions, and visual evidence

Problem framing

What I was trying to solve

This page is not just a lab description. It explains how I transformed the assignment idea into an engineering story: what the model receives, what it optimizes, what output it should produce, and how the result can be inspected.

Implementation

What I coded or assembled

The implementation focus was the mechanism behind the result: functions, model blocks, training logic, preprocessing, evaluation, and the small technical details that make the notebook work rather than only look correct.

Concepts

Core concepts

InceptionV3Transfer learningFrozen feature extractormixed7 layerBinary classification

These tags show the technical ideas this milestone added to my toolkit.

Learning result

What changed after it

This milestone showed when to reuse strong pretrained convolutional features instead of training every layer from scratch.

Important outputs and evidence

Training images: 1,027; validation images: 256
Training stopped at accuracy 0.9990
Validation accuracy around 91.96%
Test accuracy: 87.5%

How I would explain it in an interview

I would describe this milestone by starting from the data representation, then explain the model or algorithm, then show what was measured. The important part is not only the final number; it is the ability to reason about why the method works, what assumptions it makes, and what limitations should be improved next.