Simplify the creation of convolutional neural network
Project description
ECNN
Simplify the creation of convolutional neural network
Installation
Run the following to install:
pip install Easy-Convolutional-Neural-Network
Usage
from ECNN import *
####Initialise network####
my_network = ECNN.neural_network()
#Config the network
nb_input = 4
hidden_layer = [
[5,'Sigmoid'],# First layer with 5 neurons and have Sigmoid function
[3,'Tanh'],
[6,'ReLU']
]
nb_output = 1
output_function = 'Sigmoid'
#Function :
# Tanh (z)
# Sigmoid (z)
# ReLU (z)
# Binary-Step (z)
my_network.make(nb_input,hidden_layer,nb_output,output_function)
# Make the dataset
input_dataset = [
[0,0,0,1],
[0,0,1,1],
[0,1,1,1],
[1,0,1,0],
[1,1,1,1]
]
# Make the expected values
expected = [
[0],
[0],
[1],
[0],
[1]
]
# Train with dataset
iteration = 2000
# Start the training
my_network.train(input_dataset,expected,iteration,display=True)
# Make prediction values
test_inputs = [1,1,1,0]
print(my_network.predict(test_inputs))
# Save the network
my_network.save("networkData/")
# Load other network
my_network.load("networkData2/")
$ pip install -e .[dev]
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Close
Hashes for Easy-Convolutional-Neural-Network-1.1.1.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | d244ed892ef889ba96eff5681c4810ede5aef3d607c5771d5d0d972072245619 |
|
MD5 | e26a589d62b5f4922f3cb8fbfb71349f |
|
BLAKE2b-256 | a4d4e61b1d60952008c3e914afa3dcbc3d7bba59850b6a0ed360edbd6f6ab63c |
Close
Hashes for Easy_Convolutional_Neural_Network-1.1.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 1d0ce9b6e6fdbfc6f042eea6486f62e6612896a8f0d6546a4e21935f0bf02f2d |
|
MD5 | a176723f51087f5365a968ff9d07a3d2 |
|
BLAKE2b-256 | 1ccaa2ec7096438e59736bb6a93bd90509dbc798d74d2f9c2ada488aae7ec4cd |