This metric-learn repository contains Python implementations of metric learning algorithms.
Open source
24 alternativesLeanpass
Leanpass provides a lightweight implementation for computing gradients.
About Leanpass
Leanpass is a lightweight, NumPy-based automatic differentiation library for small neural network experiments. It is designed to be easy to read and simple to inspect, which makes it useful for learning how automatic differentiation works internally. The project is distributed as a repository and installs with pip.
Its source describes it as built for small-scale work rather than large models. Its documentation covers the API reference, core concepts, and guides on regression, classification, MNIST, gradient checking, and custom layers.
Key features
- Tensor objects with reverse-mode autodiff
- Activation functions: ReLU, sigmoid, softmax, tanh, LeakyReLU, and GELU
- Linear layers and multilayer perceptrons
- Loss utilities: MSE, cross-entropy, and binary cross-entropy
- SGD with momentum and L2 weight decay, and Adam with optional L2 weight decay
- Inverted dropout layer for use during training
Best for: Students and developers who want to learn how automatic differentiation works, or who need a small library for prototyping small neural network experiments.
Good for
- Depends only on NumPy
- Readable implementation without heavy abstraction
- Suited to teaching, prototyping, and small-scale experimentation
Watch out for
- Described as intended for small neural network experiments
Leanpass at a glance
- Website
- github.com/Terminay/LeanPass
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Leanpass alternatives
Tools and sites you could use instead, ranked by how closely they match.
metric-learn provides Python implementations of metric learning algorithms.
Open source
24 alternatives
This Scikit-learn extension accelerates compatible applications through optimized implementations.
Open source
24 alternatives
Opytimizer provides Python implementations of metaheuristic optimization algorithms for search problems.
Open source
24 alternatives
OpenMetricLearning provides metric learning pipelines, models, and a model zoo.
Open source
24 alternatives
Hugging Face Accelerate launches and trains PyTorch models across devices and distributed configurations.
Open source
24 alternativesPopular in ML Training & Optimization
Well-known listings from the same topic.
Edwardedwardlib.orgAerosolveaerosolve.airbnb.techDataturedatature.ioTogether AItogether.aiOptunaoptuna.orgCatBoostcatboost.ai
Leanpass FAQ
What does Leanpass depend on?
The source lists NumPy as its only dependency.
How is Leanpass installed?
It is installed with pip using the command pip install leanpass.
Where is the full documentation?
Full documentation is at leanpass.kilobyte136.workers.dev and includes the API reference, core concept explanations, hands-on guides, and a changelog.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.