Phito-Deep

Phito-Deep is a deep learning framework built from scratch with only numpy. This is being actively developed as part of my learning journey to becoming a machine learning engineer. I’m using it to better understand the underlying algorithms that power modern deep learning frameworks and architectures.

Installation

$ pip install phitodeep

Usage

MNIST quickstart:

import numpy as np
from datasets import load_dataset

from phitodeep.model import SequentialBuilder
from phitodeep.loss import CategoricalCrossEntropy
from phitodeep.optimization.optimizers import Adam
from phitodeep.optimization.initialization import Xavier, InitType

train_dataset = load_dataset("ylecun/mnist", split="train")
test_dataset = load_dataset("ylecun/mnist", split="test")

X_train = train_dataset["image"]
y_train = train_dataset["label"]
X_test = test_dataset["image"]
y_test = test_dataset["label"]

X_train = np.array(X_train).astype(np.float32) / 255.0
y_train = np.array(y_train)
X_test = np.array(X_test).astype(np.float32) / 255.0
y_test = np.array(y_test)
print(X_train.shape, y_train.shape)

model = (
    SequentialBuilder()
    .flatten()
    .dense(784, 128)
    .relu()
    .dense(128, 64, Xavier(InitType.NORMAL))
    .relu()
    .dense(64, 10, Xavier(InitType.NORMAL))
    .softmax()
    .optimizer(Adam())
    .loss(CategoricalCrossEntropy())
    .alpha(0.05)
    .epochs(5)
    .batch(64)
    .build()
)

model.summary()

model.train(X_train, y_train, X_test, y_test)

Contributing

Interested in contributing? Check out the contributing guidelines. Please note that this project is released with a Code of Conduct. By contributing to this project, you agree to abide by its terms.

License

phitodeep was created by Ralph Dugue. It is licensed under the terms of the Apache License 2.0 license.

Credits

phitodeep was created with cookiecutter and the py-pkgs-cookiecutter template.