EasyNN 0.0.24

EasyNN is a python package designed to provide an easy-to-use neural network. The package is designed to work right out of the box, while also allowing the user to customize features as they see fit.

EasyNN - Neural Networks made Easy

EasyNN is a python package designed to provide an easy-to-use Neural Network. The package is designed to work right out of the box with multiple datasets, while also allowing the user to customize features as they see fit.

EasyNN requires Python version 3.9.7 or greater.

See our wiki for more information and Datasets.

Installation:

Run python's pip3 to install:

pip3 install EasyNN

Model:

from EasyNN.examples.mnist.number.trained import model

# Classify the an image in the dataset
print(model.classify(image))

Dataset Example:

from EasyNN.examples.mnist.number.trained import model
from EasyNN.examples.mnist.number.data import dataset

images, labels = dataset

# Classify what the second image is in the dataset.
print(model.classify(images[1]))

Dataset example output:

Downloading - number_parameters.npz:
[################################] 1769/1769 - 00:00:00
Downloading - number_structure.pkl:
[################################] 10700/10700 - 00:00:00
Downloading - number_dataset.npz:
[################################] 11221/11221 - 00:00:00
0

Full example:

More info can be found about converting images in the utilities section.

from EasyNN.examples.mnist.number.trained import model
from EasyNN.utilities.image.preprocess import image
from EasyNN.utilities.download import download

# Download an example image.
download("four.jpg","https://bit.ly/3lAJrMe")

format_options = dict(
    grayscale=True,
    invert=True,
    process=True,
    contrast=30,
    resize=(28, 28),
    rotate=3,
)

# Converting your image into the correct format for the mnist number dataset.
image = image("four.jpg").format(**format_options)

print(model.classify(image))

model.show(image)

Output:

Downloading - number_parameters.npz:
[################################] 1769/1769 - 00:00:00
Downloading - number_structure.pkl:
[################################] 10700/10700 - 00:00:00
Downloading - four.jpg:
[################################] 1371/1371 - 00:00:00
4

Image output:

To see more examples with many other datasets. Please visit our wiki.