IdeaCredIdeaCred

galafis/ibm-deep-learning-capstone

54

IBM Deep Learning with PyTorch, Keras and TensorFlow Professional Certificate Capstone Project

What's novel

IBM Deep Learning with PyTorch, Keras and TensorFlow Professional Certificate Capstone Project

Code Analysis

9 files read · 3 rounds

A textbook CNN builder/trainer class for image classification paired with a Streamlit dashboard that displays simulated (not real) training metrics and a random confusion matrix.

Strengths

The CNN architecture is correctly structured with BatchNormalization, Dropout, EarlyStopping, and ReduceLROnPlateau callbacks, and the Streamlit dashboard is well-organized with clean Plotly visualizations and correct precision/recall/F1 formulas.

Weaknesses

The dashboard displays entirely fabricated data (exponential decay + noise) with no connection to the actual model, the tests are pure placeholders (2+2==4) that never import project code, and the docs reference methods that don't exist.

Score Breakdown

Innovation
2 (25%)
Craft
61 (35%)
Traction
6 (15%)
Scope
49 (25%)

Signal breakdown

Innovation

Not Fork+1
Code Novelty+0
Concept Novelty+0

Craft

Ci-2
Tests+8
Polish+1
Releases+0
Has License+5
Code Quality+15
Readme Quality+15
Recent Activity+7
Structure Quality+5
Commit Consistency+2
Has Dependency Mgmt+5

Traction

Forks+0
Stars+6
Hn Points+0
Watchers+0
Early Traction+0
Devto Reactions+0
Community Contribs+0

Scope

Commits+5
Languages+5
Subsystems+5
Bloat Penalty+0
Completeness+7
Contributors+5
Authored Files+8
Readme Code Match+3
Architecture Depth+3
Implementation Depth+8

Evidence

Commits

10

Contributors

1

Files

12

Active weeks

5

TestsCI/CDREADMELicenseContributing

Repository

Language

Python

Stars

1

Forks

0

License

MIT