TensorFlow Developer Specialization · CNNs in TensorFlow

Rock Paper Scissors Classifier

A 3-class CNN with data augmentation and an upload-style prediction workflow for rock, paper, and scissors hand images.

Data augmentationMulti-class image classificationtf.data performanceDropoutUpload prediction

What this project is about

This project combines a CNN with data augmentation and an upload-prediction workflow. It is a practical image-classification app pattern, not only a training notebook.

Implementation focus

The important lesson was generalization: augmentation helps the model see variations in rotation, position, contrast, and zoom before it sees new validation examples.

Key results and artifacts

Training files: 2,521
Validation files: 372
Final validation accuracy: ~97.31%
Strong validation peaks around 99%

What I learned

This milestone introduced stronger augmentation and an application-like prediction flow on top of a CNN classifier.

Milestone deep dive

What this project proves in my learning path.

A 3-class CNN with data augmentation and an upload-style prediction workflow for rock, paper, and scissors hand images. 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

Data augmentationMulti-class image classificationtf.data performanceDropoutUpload prediction

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

Learning result

What changed after it

This milestone introduced stronger augmentation and an application-like prediction flow on top of a CNN classifier.

Important outputs and evidence

Training files: 2,521
Validation files: 372
Final validation accuracy: ~97.31%
Strong validation peaks around 99%

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.