TensorFlow Developer Specialization · CNNs in TensorFlow

Sign Language Multi-Class Classifier

A compact CNN for 24-class Sign Language MNIST classification, moving from binary classification to multi-class visual recognition.

Multi-class CNNGrayscale imagesCategorical labelsSoftmax classifierGesture recognition

GitHub

What this project is about

The sign-language milestone moves from binary classification to 24 classes. It uses grayscale input and a compact CNN to classify static hand-letter images.

Implementation focus

The learning was about multi-class output design: categorical labels, softmax probabilities, validation behavior, and compact CNN architecture for small images.

Key results and artifacts

Training files: 27,455
Validation files: 7,173
Classes: 24 letters
Final validation accuracy: ~89.04%

What I learned

This project made the classification head more realistic: many visual classes, small images, and a clean preprocessing path.

Milestone deep dive

What this project proves in my learning path.

A compact CNN for 24-class Sign Language MNIST classification, moving from binary classification to multi-class visual recognition. 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 layerordered sequences of text, audio, dates, or musical events

Model layerrecurrent or attention-based sequence model

Evaluation layertests, metrics, plots, or qualitative output

Artifact layerclassification, generation, alignment, or trigger probabilities

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

Multi-class CNNGrayscale imagesCategorical labelsSoftmax classifierGesture recognition

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

Learning result

What changed after it

This project made the classification head more realistic: many visual classes, small images, and a clean preprocessing path.

Important outputs and evidence

Training files: 27,455
Validation files: 7,173
Classes: 24 letters
Final validation accuracy: ~89.04%

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.