Skip to main content

Mini-framework that implements a simple version of a feedforward neural network (FNN) and convolutional neural network (CNN) from scratch using Python and PyTorch

Project description

Custom Neural Network Framework

This repository is a mini-framework that implements a simple version of a feedforward neural network (FNN) and convolutional neural network (CNN) from scratch using Python and PyTorch. PyTorch is used solely for mathematical and element-wise operations on tensors (without using autograd), and for speeding up computations by utilizing the GPU. Simply put, PyTorch is used as a replacement for NumPy but with GPU acceleration. The framework provides basic functionalities for building, training, and evaluating custom neural network models for both regression and classification tasks.

Features

  • Feedforward Neural Network (FNN): A fully connected neural network suitable for regression and classification tasks.
  • Convolutional Neural Network (CNN): A simplified CNN implementation with convolutional and max-pooling layers.
  • Activation Functions: Includes ReLU, Leaky ReLU, Sigmoid, and Linear activations.
  • Loss Functions: Support for mean squared error (MSE), binary cross-entropy (BCE) and categorical cross-entropy (CCE) losses.
  • Optimizers: Implementations of stochastic gradient descent (SGD) and Adam optimizers.
  • Metrics: Accuracy metric for classification tasks, especially useful for one-hot encoded data, and R2 score for regression tasks.

Installation

pip install vladk-neural-network

Usage

Data Format examples:

Example for regression:

# sample shape (2, 1) - 2 input values, 1 output value
dataset = [
    {
        "input": [0.1, 0.2],
        "output": [0.15],
    },
    {
        "input": [0.8, 0.9],
        "output": [0.7],
    },
]

Example for classification, output values one-hot encoded:

# sample shape (4, 2) - 4 input values, 2 output one-hot encoded values
dataset = [
    {
        "input": [0.13, 0.22, 0.37, 0.41],
        "output": [1.0, 0.0],
    },
    {
        "input": [0.76, 0.87, 0.91, 0.93],
        "output": [0.0, 1.0],
    },
]

Model creation examples:

Feedforward Neural Network for regression:

from vladk_neural_network.model.activation import Linear, Relu
from vladk_neural_network.model.base import NeuralNetwork
from vladk_neural_network.model.layer import FullyConnected, Input
from vladk_neural_network.model.loss import MeanSquaredError
from vladk_neural_network.model.metric import R2Score
from vladk_neural_network.model.optimizer import SGD

# Build model
layers = [
    FullyConnected(64, Relu()),
    FullyConnected(64, Relu()),
    FullyConnected(1, Linear()),
]
nn = NeuralNetwork(
    Input(2),
    layers,
    optimizer=SGD(),
    loss=MeanSquaredError(),
    metric=R2Score()
)

# Train model
history = nn.fit(train_dataset, test_dataset, epochs=20, batch_size=1, verbose=True)

# Using model for prediction
prediction = nn.predict(test_dataset)

Convolutional Neural Network for classification:

from vladk_neural_network.model.activation import LeakyRelu, Linear
from vladk_neural_network.model.base import NeuralNetwork
from vladk_neural_network.model.layer import (
    Convolutional,
    Flatten,
    FullyConnected,
    Input3D,
    MaxPool2D,
)
from vladk_neural_network.model.loss import CategoricalCrossEntropy
from vladk_neural_network.model.metric import AccuracyOneHot
from vladk_neural_network.model.optimizer import Adam

# Build model using gpu acceleration and applying argmax convert to raw prediction probabilities
layers = [
    Convolutional(LeakyRelu(), filters_num=4, kernel_size=3, padding_type="same"),
    Convolutional(LeakyRelu(), filters_num=8, kernel_size=3),
    Convolutional(LeakyRelu(), filters_num=16, kernel_size=3),
    MaxPool2D(),
    Flatten(),
    FullyConnected(64, LeakyRelu()),
    FullyConnected(10, Linear()),
]
cnn = NeuralNetwork(
    Input3D((1, 28, 28)),
    layers,
    optimizer=Adam(),
    loss=CategoricalCrossEntropy(),
    metric=AccuracyOneHot(),
    convert_prediction='argmax',
    use_gpu=True
)

# Train model
cnn.fit(train_dataset, test_dataset, epochs=10, batch_size=1, verbose=True)

# Using model for prediction
prediction = cnn.predict(test_dataset)

Several examples, including training feedforward and convolutional neural networks, are available in the form of Jupyter notebooks in the notebooks/ folder. You can view and run these examples to understand how to use the framework for different tasks.

License

This project is licensed under the MIT License. See the LICENSE file for more details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

vladk_neural_network-0.1.10.tar.gz (12.4 kB view details)

Uploaded Source

Built Distribution

vladk_neural_network-0.1.10-py3-none-any.whl (12.8 kB view details)

Uploaded Python 3

File details

Details for the file vladk_neural_network-0.1.10.tar.gz.

File metadata

  • Download URL: vladk_neural_network-0.1.10.tar.gz
  • Upload date:
  • Size: 12.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.12.3 Linux/6.8.0-44-generic

File hashes

Hashes for vladk_neural_network-0.1.10.tar.gz
Algorithm Hash digest
SHA256 8b720fa6d489691d2258571259cea216b2ab3adac321c2f11bbd5d4dc95d0af8
MD5 e4b77735ef2c2e2972998764d05c05e5
BLAKE2b-256 6955fe3c2be4fa12b463765016e477ec57d39b57d22802b6341423a8eaef3733

See more details on using hashes here.

File details

Details for the file vladk_neural_network-0.1.10-py3-none-any.whl.

File metadata

File hashes

Hashes for vladk_neural_network-0.1.10-py3-none-any.whl
Algorithm Hash digest
SHA256 b3db526b807219a2f54c0664c443b373dd5c990057b2985fdecaa25d9d0a5a68
MD5 76c755f9115ef33939c066cc05404ace
BLAKE2b-256 709207eeb257f3987c51e3f590c5dcc97c580882a1a91638ee837bae290b5d41

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page