from Mnist import Mnist
from Network import Network
m = Mnist('train-images-idx3-ubyte', 'train-labels-idx1-ubyte',
't10k-images-idx3-ubyte', 't10k-labels-idx1-ubyte')
net = Network([784, 30, 10])
net.SGD(m.train_data, 30, 10, 3.0, test_data=m.test_data)
print("We now have a network with random assignments for weights and biases.")
print("It probably won't do so well... Let's see.")
input(
"Before we train, let's get a baseline. Here is how the network performs on a set of testing images. (Press Enter)."
)
network.evaluate(test_data)
print(
"Probably not so great. Let's train the network to recognize these digits."
)
print("Watch the weights and biases change as the network is trained.")
input("Press enter to begin training.")
network.SGD(training_data,
mini_batch_size,
learning_rate,
epochs,
updates=True)
print("Now that the network is trained, let's see how it does with"
"images it has never seen before!")
wrong = network.evaluate(test_data)
input("Probably a lot better!\n")
input(
"Let's see what it got wrong. Press Enter to scroll through the network's guesses."
)
nd = NetDraw()
from Network import Network
from MNIST import MNIST
import numpy as np
if __name__ == '__main__':
mnist = MNIST()
training_data, validation_data, test_data = mnist.load_mnist_wrapper(
factor=0.8, num_class=10)
# training_data, validation_data, test_data = load_data_wrapper()
net = Network(sizes=[784, 30, 20, 10],
training_data=training_data,
test_data=test_data,
validation_data=validation_data,
learning_rate=2.5,
mini_batch_size=16,
epochs=30)
net.SGD()
print ("Running with a CPU. If this is not desired, then the modify "+\
"network3.py to set\nthe GPU flag to True.")
training_data, validation_data, test_data = load_data_shared()
mini_batch_size = 10
from Network import Network
from FullyConnectedLayer import FullyConnectedLayer
from SoftmaxLayer import SoftmaxLayer
from ConvPoolLayer import ConvPoolLayer
net = Network([
FullyConnectedLayer(n_in=784, n_out=100),
SoftmaxLayer(n_in=100, n_out=10)
], mini_batch_size)
net.SGD(training_data, 1, mini_batch_size, 0.1, validation_data, test_data)
# add a convolutional layer:
net = Network([
ConvPoolLayer(image_shape=(mini_batch_size, 1, 28, 28),
filter_shape=(20, 1, 5, 5),
poolsize=(2, 2)),
FullyConnectedLayer(n_in=20*12*12, n_out=100),
SoftmaxLayer(n_in=100, n_out=10)],
mini_batch_size)
net.SGD(training_data, 60, mini_batch_size, 0.1, validation_data, test_data)
expanded_training_data, _, _ = load_data_shared("../../neural-networks-and-deep-learning/data/mnist_expanded.pkl.gz")
#coding:utf-8 from Network import Network import mnist_loader training_data, validation_data, test_data = mnist_loader.load_data_wrapper() net = Network([784, 30, 10]) net.SGD(training_data, 30, 10, 3.0, test_data=test_data) exit(0)
import load_data
from Convolutional_Network import CNNetwork
from Network import Network
import numpy as np
training_data, patch_data, validation_data, test_data = load_data.load_data_wrapper(
)
netff0 = Network([784, 100, 25, 10])
netff0.SGD(training_data[:10000], 10, 10, .5, test_data=test_data[:100])
netcff0 = CNNetwork([100, 25, 10],
patch_data,
n_clusters=16,
patch_size=(8, 8),
pool_size=(5, 5))
netcff0.SGD(training_data[:10000],
10,
10,
.5,
test_data=test_data[:100],
convolve=True)
np.random.seed(seed=0)
altered_training_data = [(load_data.random_maniputlate_image(img), key)
for img, key in training_data[:10000]]
altered_test_data = [(load_data.random_maniputlate_image(img), key)
for img, key in test_data[:100]]
netcff1 = CNNetwork([100, 25, 10],
patch_data,
n_clusters=16,
import numpy as np
import idx2numpy
import matplotlib.pyplot as plt
from Network import Network
epochs = 30
network_architecture = [784, 20, 10]
train_images_file = 'train-images.idx3-ubyte'
train_images_array = idx2numpy.convert_from_file(train_images_file)
input_matrix = np.reshape(train_images_array, (60000, 28 * 28)) / 500
train_labels_file = 'train-labels.idx1-ubyte'
train_labels_array = idx2numpy.convert_from_file(train_labels_file)
test_images_file = 't10k-images.idx3-ubyte'
test_images_array = idx2numpy.convert_from_file(test_images_file)
input_matrix_test = np.reshape(test_images_array, (10000, 28 * 28))
input_matrix_test = np.reshape(test_images_array, (10000, 28 * 28)) / 500
test_labels_file = 't10k-labels.idx1-ubyte'
test_labels_array = idx2numpy.convert_from_file(test_labels_file)
network1 = Network(network_architecture)
network1.SGD(input_matrix, train_labels_array, epochs, input_matrix_test,
test_labels_array)
#coding=utf-8
from Network import Network
from mnist_loader import *
model = Network([784, 20, 20, 10])
train, val, test = load_data_wrapper('./data/mnist.pkl.gz')
model.SGD(train, 50, 2000, 0.8, val)
def start():
m = Mnist('train-images-idx3-ubyte', 'train-labels-idx1-ubyte',
't10k-images-idx3-ubyte', 't10k-labels-idx1-ubyte')
net = Network([784, 30, 10])
net.SGD(m.train_data, 30, 10, 3.0, test_data=m.test_data)