Algorithm that allows neural network to grow while training
Project description
growingnn
Framework that implements an algorithm allowing a neural network to grow while training
Usage
Simple query
x_train, x_test, y_train, y_test, labels = data_reader.read_mnist_data(mnist_path, 0.9)
gnn.trainer.train(
x_train = x_train,
y_train = y_train,
x_test = x_test,
y_test = y_test,
labels = labels,
input_paths = 1,
path = "./result",
model_name = "GNN_model",
epochs = 10,
generations = 10,
input_size = 28 * 28,
hidden_size = 28 * 28,
output_size = 10,
input_shape = (28, 28, 1),
kernel_size = 3,
depth = 2
)
This code trains a simple network on the MNIST dataset
Credits
Szymon Świderski Agnieszka Jastrzębska
Disclosure
This is the first beta version of this package. I am not liable for the accuracy of this program’s output nor actions performed based upon it.
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
growingnn-0.0.1.tar.gz
(20.6 kB
view hashes)
Built Distribution
growingnn-0.0.1-py3-none-any.whl
(23.8 kB
view hashes)
Close
Hashes for growingnn-0.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 2384be5246e9df7f1b31c159a9780667eaeeb68db77e42671144946e7130ff4b |
|
MD5 | c26e191bd9a2487c35ae83f8bd62cb2e |
|
BLAKE2b-256 | 8e47f088a209b347c301fe917ecb879a2a326bf3bb861dc0cbe32130673ec7af |