galafis/ibm-deep-learning-capstone
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 roundsA 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
Signal breakdown
Innovation
Craft
Traction
Scope
Evidence
Commits
10
Contributors
1
Files
12
Active weeks
5
Repository
Language
Python
Stars
1
Forks
0
License
MIT