a beautifully compact machine-learning library
Project description
froog 
froog: fast real-time optimization of gradients
a beautifully compact machine-learning library
homepage | documentation | pip
froog is extremely simple, with a goal of running ml on any device, by any human, easily and efficiently
Installation
pip install froog
Overview of Features
- Tensors
- Automatic Differentiation
- Forward and backward passes
- Input/gradient shape-tracking
- MNIST example
- 2D Convolutions (im2col)
- Numerical gradient checking
- The most common optimizers (SGD, Adam, RMSProp)
Math Operations
- Scalar-Matrix Multiplication
- Dot Product
- Sum
- ReLU
- Log Softmax
- 2D Convolutions
- Avg & Max pooling
- More
Bounties
Want to help but don't know where to start? Here are some bounties for you to claim
Small
- binary cross entropy
- flatten
- batch_norm
- div
- pow
- dropout
Medium
- start doing ops with opencl
- simplify how context and gradients are handled
- efficient net
Large
- transformers
- stable diffusion
- winograd convs
- MPS support
- CUDA support
Contributing
Here are the rules for contributing:
- increase simplicity
- increase efficiency
- increase functionality
more info on contributing
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
froog-0.1.8.tar.gz
(16.2 kB
view details)
Built Distribution
froog-0.1.8-py3-none-any.whl
(20.1 kB
view details)
File details
Details for the file froog-0.1.8.tar.gz.
File metadata
- Download URL: froog-0.1.8.tar.gz
- Upload date:
- Size: 16.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | c814e9b343b0217d1d69683af9d69ca8a13194e036806574db72d2f2fd7d1cab |
|
| MD5 | 3d1e55decf21464518a9c2fb1fcf84a0 |
|
| BLAKE2b-256 | a9ff8eaa171e361c341a5eae29a861017205473738b24efdb3d9dfcc534609d9 |
File details
Details for the file froog-0.1.8-py3-none-any.whl.
File metadata
- Download URL: froog-0.1.8-py3-none-any.whl
- Upload date:
- Size: 20.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 9059e07c3cff41b90d7ff60c16f56c531288af58bd095c4109b1d475a0345277 |
|
| MD5 | fa1ce04d656ad27d8c7303ce5f61ea04 |
|
| BLAKE2b-256 | 95d097890291f0d0b297c789ddb014ecf3a545d2589e75211a33b39b676a4518 |
