ArjunSahlot/TensorNN

Python machine learning library made from scratch.

What's novel

Python machine learning library made from scratch.

Code Analysis

0 files read · 5 rounds

A minimal educational neural network library built from scratch on NumPy providing basic layers, activations, optimizers, and loss functions for simple ML tasks.

Strengths

Clean separation of concerns with dedicated modules for tensors, layers, activations, losses, and optimizers. Good documentation structure with Sphinx setup and examples provided.

Weaknesses

Lacks comprehensive error handling and edge case coverage. Tests are minimal and don't cover complex scenarios. Implementation is essentially standard boilerplate without novel algorithms or optimizations.

Score Breakdown

Innovation

3 (25%)

Craft

72 (35%)

Traction

9 (15%)

Scope

63 (25%)

Signal breakdown

Innovation

Not Fork+1

Code Novelty+0

Concept Novelty+0

Craft

Ci+5

Tests+8

Polish+2

Releases+3

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+3

Early Traction+0

Devto Reactions+0

Community Contribs+0

Scope

Commits+5

Languages+3

Subsystems+10

Bloat Penalty+0

Completeness+7

Contributors+5

Authored Files+12

Readme Code Match+3

Architecture Depth+5

Implementation Depth+8

Evidence

Commits

Contributors

Files

Active weeks

TestsCI/CDREADMELicenseContributing

Repository

Language

Python

Stars

Forks

License

GPL-3.0