def double_fc_dropout(p0, p1, p2, repetitions):
expanded_training_data, _, _ = network3_nbb.load_data_shared(
"../data/mnist_expanded.pkl.gz")
nets = []
for j in range(repetitions):
print "\n\nTraining using a dropout network with parameters ",p0,p1,p2
print "Training with expanded data, run num %s" % j
net = Network([
ConvPoolLayer(image_shape=(mini_batch_size, 1, 28, 28),
filter_shape=(20, 1, 5, 5),
poolsize=(2, 2),
activation_fn=ReLU),
ConvPoolLayer(image_shape=(mini_batch_size, 20, 12, 12),
filter_shape=(40, 20, 5, 5),
poolsize=(2, 2),
activation_fn=ReLU),
FullyConnectedLayer(
n_in=40*4*4, n_out=1000, activation_fn=ReLU, p_dropout=p0),
FullyConnectedLayer(
n_in=1000, n_out=1000, activation_fn=ReLU, p_dropout=p1),
SoftmaxLayer(n_in=1000, n_out=10, p_dropout=p2)], mini_batch_size)
net.SGD(expanded_training_data, 40, mini_batch_size, 0.03,
validation_data, test_data)
nets.append(net)
return nets
def load():
import numpy as np
import time
import network3_nbb
print "...in load, using " + network3_nbb.theano.config.device
training_data, validation_data, test_data = network3_nbb.load_data_shared()
mini_batch_size = 10
def expanded_data_double_fc(n=100):
"""n is the number of neurons in both fully-connected layers. We'll
try n=100, 300, and 1000.
"""
expanded_training_data, _, _ = network3_nbb.load_data_shared(
"../data/mnist_expanded.pkl.gz")
for j in range(3):
print "Training with expanded data, %s neurons in two FC layers, run num %s" % (n, j)
net = Network([
ConvPoolLayer(image_shape=(mini_batch_size, 1, 28, 28),
filter_shape=(20, 1, 5, 5),
poolsize=(2, 2),
activation_fn=ReLU),
ConvPoolLayer(image_shape=(mini_batch_size, 20, 12, 12),
filter_shape=(40, 20, 5, 5),
poolsize=(2, 2),
activation_fn=ReLU),
FullyConnectedLayer(n_in=40*4*4, n_out=n, activation_fn=ReLU),
FullyConnectedLayer(n_in=n, n_out=n, activation_fn=ReLU),
SoftmaxLayer(n_in=n, n_out=10)], mini_batch_size)
net.SGD(expanded_training_data, 60, mini_batch_size, 0.03,
validation_data, test_data, lmbda=0.1)
def dbl_conv_relu(lmbda_epochs):
import numpy as np
import time
import network3_nbb
print "...in dbl_conv_relu, using " + network3_nbb.theano.config.device
training_data, validation_data, test_data = network3_nbb.load_data_shared()
mini_batch_size = 10
lmbda = lmbda_epochs[0]
epoch = lmbda_epochs[1]
print "Conv + Conv + FC num %s, relu, with regularization. lambda: %s, epochs: %s" % (
0, lmbda, epoch)
net = network3_nbb.Network([
network3_nbb.ConvPoolLayer(image_shape=(mini_batch_size, 1, 28, 28),
filter_shape=(20, 1, 5, 5),
poolsize=(2, 2),
activation_fn=network3_nbb.ReLU),
network3_nbb.ConvPoolLayer(image_shape=(mini_batch_size, 20, 12, 12),
filter_shape=(40, 20, 5, 5),
poolsize=(2, 2),
activation_fn=network3_nbb.ReLU),
network3_nbb.FullyConnectedLayer(
n_in=40 * 4 * 4, n_out=100, activation_fn=network3_nbb.ReLU),
network3_nbb.SoftmaxLayer(n_in=100, n_out=10)
], mini_batch_size)
acc_array = net.SGD(training_data,
int(epoch),
mini_batch_size,
0.03,
validation_data,
test_data,
lmbda=lmbda)
return [acc_array, lmbda, epoch]
import numpy as np
import time
import network3_nbb
print "Starting, using " + network3_nbb.theano.config.device
training_data, validation_data, test_data = network3_nbb.load_data_shared()
mini_batch_size = 10
lmbda = 0.1 #lmbda_epochs[0]
epoch = 2 #lmbda_epochs[1]
print "Conv + Conv + FC num %s, relu, with regularization. lambda: %s, epochs: %s" % (
0, lmbda, epoch)
net = network3_nbb.Network([
network3_nbb.ConvPoolLayer(image_shape=(mini_batch_size, 1, 28, 28),
filter_shape=(20, 1, 5, 5),
poolsize=(2, 2),
activation_fn=network3_nbb.ReLU),
network3_nbb.ConvPoolLayer(image_shape=(mini_batch_size, 20, 12, 12),
filter_shape=(40, 20, 5, 5),
poolsize=(2, 2),
activation_fn=network3_nbb.ReLU),
network3_nbb.FullyConnectedLayer(
n_in=40 * 4 * 4, n_out=100, activation_fn=network3_nbb.ReLU),
network3_nbb.SoftmaxLayer(n_in=100, n_out=10)
], mini_batch_size)
acc_array = net.SGD(training_data,
int(epoch),
mini_batch_size,
0.03,