froog 0.2.6

a beautifully simplistic ml framework

froog

froog: fast real-time optimization of gradients
a beautifully compact machine-learning library
homepage | documentation | pip

froog is a SUPER SIMPLE machine learning framework with the goal of creating tools with AI --> easily and efficiently.

froog encapsulates everything from linear regression to convolutional neural networks

all of this in under 1000 lines. in the tadpole folder.

Installation

pip install froog

Overview of Features

• Custom Tensors
  • Backpropagation
  • Automatic Differentiation (autograd)
    • Forward and backward passes
• ML Operations
  • 2D Convolutions (im2col)
  • Numerical gradient checking
  • Acceleration methods (Adam)
  • Avg & Max pooling
• EfficientNet inference
• GPU Support
• and a bunch more

Sneak Peek

from froog.tensor import Tensor
from froog.nn import Linear
import froog.optim as optim

class mnistMLP:
  def __init__(self):
    self.l1 = Tensor(Linear(784, 128))
    self.l2 = Tensor(Linear(128, 10))

  def forward(self, x):
    return x.dot(self.l1).relu().dot(self.l2).logsoftmax()

model = mnistMLP()
optim = optim.SGD([model.l1, model.l2], lr=0.001)

Bounties

THERES LOT OF STUFF TO WORK ON! VISIT THE BOUNTY SHOP

Pull requests will be merged if they:

• increase simplicity
• increase functionality
• increase efficiency

more info on contributing