Loading repository data…
ahmedfgad / repository
Building Convolutional Neural Networks From Scratch using NumPy
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
NumPyCNN is a Python implementation for convolutional neural networks (CNNs) from scratch using NumPy.
IMPORTANT If you are coming for the code of the tutorial titled Building Convolutional Neural Network using NumPy from Scratch, then it has been moved to the TutorialProject directory on 20 May 2020.
The project has a single module named cnn.py which implements all classes and functions needed to build the CNN.
It is very important to note that the project only implements the forward pass of training CNNs and there is no learning algorithm used. Just the learning rate is used to make some changes to the weights after each epoch which is better than leaving the weights unchanged.
The project can be used for classification problems where only 1 class per sample is allowed.
The project will be extended to train CNN using the genetic algorithm with the help of a library named PyGAD. Check the library's documentation at Read The Docs: https://pygad.readthedocs.io
To install PyGAD, simply use pip to download and install the library from PyPI (Python Package Index). The library is at PyPI at this page https://pypi.org/project/pygad.
Install PyGAD with the following command:
pip install pygad
To get started with PyGAD, please read the documentation at Read The Docs https://pygad.readthedocs.io.
The source code of the PyGAD' modules is found in the following GitHub projects:
The documentation of PyGAD is available at Read The Docs https://pygad.readthedocs.io.
The documentation of the PyGAD library is available at Read The Docs at this link: https://pygad.readthedocs.io. It discusses the modules supported by PyGAD, all its classes, methods, attribute, and functions. For each module, a number of examples are given.
If there is an issue using PyGAD, feel free to post at issue in this GitHub repository https://github.com/ahmedfgad/GeneticAlgorithmPython or by sending an e-mail to ahmed.f.gad@gmail.com.
If you built a project that uses PyGAD, then please drop an e-mail to ahmed.f.gad@gmail.com with the following information so that your project is included in the documentation.
Please check the Contact Us section for more contact details.
The next figure lists the different stages in the lifecycle of an instance of the pygad.GA class. Note that PyGAD stops when either all generations are completed or when the function passed to the on_generation parameter returns the string stop.
The next code implements all the callback functions to trace the execution of the genetic algorithm. Each callback function prints its name.
import pygad
import numpy
function_inputs = [4,-2,3.5,5,-11,-4.7]
desired_output = 44
def fitness_func(ga_instance, solution, solution_idx):
output = numpy.sum(solution*function_inputs)
fitness = 1.0 / (numpy.abs(output - desired_output) + 0.000001)
return fitness
fitness_function = fitness_func
def on_start(ga_instance):
print("on_start()")
def on_fitness(ga_instance, population_fitness):
print("on_fitness()")
def on_parents(ga_instance, selected_parents):
print("on_parents()")
def on_crossover(ga_instance, offspring_crossover):
print("on_crossover()")
def on_mutation(ga_instance, offspring_mutation):
print("on_mutation()")
def on_generation(ga_instance):
print("on_generation()")
def on_stop(ga_instance, last_population_fitness):
print("on_stop()")
ga_instance = pygad.GA(num_generations=3,
num_parents_mating=5,
fitness_func=fitness_function,
sol_per_pop=10,
num_genes=len(function_inputs),
on_start=on_start,
on_fitness=on_fitness,
on_parents=on_parents,
on_crossover=on_crossover,
on_mutation=on_mutation,
on_generation=on_generation,
on_stop=on_stop)
ga_instance.run()
Based on the used 3 generations as assigned to the num_generations argument, here is the output.
on_start()
on_fitness()
on_parents()
on_crossover()
on_mutation()
on_generation()
on_fitness()
on_parents()
on_crossover()
on_mutation()
on_generation()
on_fitness()
on_parents()
on_crossover()
on_mutation()
on_generation()
on_stop()
Check the PyGAD's documentation for information about the implementation of this example.
import numpy
import pygad.cnn
train_inputs = numpy.load("dataset_inputs.npy")
train_outputs = numpy.load("dataset_outputs.npy")
sample_shape = train_inputs.shape[1:]
num_classes = 4
input_layer = pygad.cnn.Input2D(input_shape=sample_shape)
conv_layer1 = pygad.cnn.Conv2D(num_filters=2,
kernel_size=3,
previous_layer=input_layer,
activation_function=None)
relu_layer1 = pygad.cnn.Sigmoid(previous_layer=conv_layer1)
average_pooling_layer = pygad.cnn.AveragePooling2D(pool_size=2,
previous_layer=relu_layer1,
stride=2)
conv_layer2 = pygad.cnn.Conv2D(num_filters=3,
kernel_size=3,
previous_layer=average_pooling_layer,
activation_function=None)
relu_layer2 = pygad.cnn.ReLU(previous_layer=conv_layer2)
max_pooling_layer = pygad.cnn.MaxPooling2D(pool_size=2,
previous_layer=relu_layer2,
stride=2)
conv_layer3 = pygad.cnn.Conv2D(num_filters=1,
kernel_size=3,
previous_layer=max_pooling_layer,
activation_function=None)
relu_layer3 = pygad.cnn.ReLU(previous_layer=conv_layer3)
pooling_layer = pygad.cnn.AveragePooling2D(pool_size=2,
previous_layer=relu_layer3,
stride=2)
flatten_layer = pygad.cnn.Flatten(previous_layer=pooling_layer)
dense_layer1 = pygad.cnn.Dense(num_neurons=100,
previous_layer=flatten_layer,
activation_function="relu")
dense_layer2 = pygad.cnn.Dense(num_neurons=num_classes,
previous_layer=dense_layer1,
activation_function="softmax")
model = pygad.cnn.Model(last_layer=dense_layer2,
epochs=1,
learning_rate=0.01)
model.summary()
model.train(train_inputs=train_inputs,
train_outputs=train_outputs)
predictions = model.predict(data_inputs=train_inputs)
print(predictions)
num_wrong = numpy.where(predictions != train_outputs)[0]
num_correct = train_outputs.size - num_wrong.size
accuracy = 100 * (num_correct/train_outputs.size)
print("Number of correct classifications : {num_correct}.".format(num_correct=num_correct))
print("Number of wrong classifications : {num_wrong}.".format(num_wrong=num_wrong.size))
print("Classification accuracy : {accuracy}.".format(accuracy=accuracy))
There are different resources that can be used to get started with the building CNN and its Python implementation.
To start with coding the genetic algorithm, you can check the tutorial titled Genetic Algorithm Implementation in Python available at these links:
This tutorial is prepared based on a previous version of the project but it still a good resource to start with coding the genetic algorithm.
Get started with the genetic algorithm by reading the tutorial titled Introduction to Optimization with Genetic Algorithm which is available at these links:
Read about building neural networks in Python through the tutorial titled Artificial Neural Network Implementation using NumPy and Classification of the Fruits360 Image Dataset available at these links:
Selected from shared topics, language and repository description—not editorial ratings.
ahmedfgad /
Building a HTTP-accessed convolutional neural network model using TensorFlow NN (tf.nn), CIFAR10 dataset, Python and Flask.
43/100 healthCharmve /
Building Convolutional Neural Networks From Scratch using NumPy
35/100 healthriccardotenuta /
Machine learning project which focus on building a classification model with a convolutional neural network to recognize face emotions in a photo. This project has been developed in team and it's been realised totally in Python.
30/100 healthftm-zarin /
Implements Neural Style Transfer with PyTorch and explores CNN fundamentals by building a convolutional layer from scratch.
48/100 healthmyladivyasaisri /
An intermediate-level Deep Learning project building a Convolutional Neural Network (CNN) with TensorFlow & Keras on the MNIST dataset, developed as Task 4 during my Machine Learning internship at VedGrow. Includes augmentation pipelines and accuracy tracking charts.
62/100 healthLuke-Dev-Tech /
This repository presents a collaborative project on recycling material classification using a Convolutional Neural Network (CNN) based on EfficientNet-B2. It focuses on building an image classification system capable of identifying different types of recyclable materials, combining practical implementation with modern deep learning techniques.
58/100 health