froog 0.2.7

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.

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