Getting Started

Getting Started with PyDeepFlow

This guide will walk you through the steps to install PyDeepFlow and run your first neural network model.

Installation:

PyDeepFlow requires Python 3.x and supports both CPU (via NumPy) and GPU (via CuPy) computation. Follow the steps below to install the necessary dependencies.

1. Install PyDeepFlow:

   pip install pydeepflow
   

2. (Optional) Install CuPy for GPU Support: If you want to leverage your GPU for faster computations, install CuPy. Use the appropriate version based on your CUDA setup:

   pip install cupy-cuda11x
   

   (Replace 11x with the CUDA version you have installed.)

Running Your First Model:

Here's a simple example of building and training a model with PyDeepFlow:

import numpy as np
from pydeepflow.model import Multi_Layer_ANN

# Create some dummy data
X_train = np.random.randn(1000, 10)
y_train = np.random.randint(0, 2, size=(1000, 1))

# Define and compile the model
model = Multi_Layer_ANN(X_train, y_train, hidden_layers=[64, 32], activations=['relu', 'relu'], loss='binary_crossentropy')

# Train the model
model.fit(epochs=50, learning_rate=0.001)

That's it! You’ve trained your first model using PyDeepFlow!

For more detailed examples and advanced setups, head over to the Examples section.