def train(self, train, hidden_size, debug = True):
self.layout = (hidden_size, train.shape[0])
self.sample_size = train.shape[1]
theta = initialize(hidden_size, train.shape[0])
self.activations[0] = train
if debug:
self.check_gradient(theta)
else:
options = {'maxiter': 500, 'disp': True}
J = lambda x: self.forward_back(theta = x, debug = False)
result = minimize(J, theta, method='L-BFGS-B', jac=True, options=options)
opt_theta = result.x
print opt_theta
# This loads our training data from the MNIST database files.
train_images = load_MNIST.load_MNIST_images(
'data/mnist/train-images-idx3-ubyte')
train_labels = load_MNIST.load_MNIST_labels(
'data/mnist/train-labels-idx1-ubyte')
##======================================================================
## STEP 2: Train the first sparse autoencoder
# This trains the first sparse autoencoder on the unlabelled STL training
# images.
# If you've correctly implemented sparseAutoencoderCost.m, you don't need
# to change anything here.
# Randomly initialize the parameters
sae1_theta = sparse_autoencoder.initialize(hidden_size_L1, input_size)
J = lambda x: sparse_autoencoder.sparse_autoencoder_cost(
x, input_size, hidden_size_L1, lambda_, sparsity_param, beta, train_images)
options_ = {'maxiter': 400, 'disp': True}
result = scipy.optimize.minimize(J,
sae1_theta,
method='L-BFGS-B',
jac=True,
options=options_)
sae1_opt_theta = result.x
print(result)
##======================================================================
##======================================================================
## STEP 1: Implement sampleIMAGES
#
# After implementing sampleIMAGES, the display_network command should
# display a random sample of 200 patches from the dataset
# Loading Sample Images
# patches = sample_images.sample_images()
# Loading 10K images from MNIST database
images = load_MNIST.load_MNIST_images('data/mnist/train-images-idx3-ubyte')
patches = images[:, 0:10000]
# Obtain random parameters theta
theta = sparse_autoencoder.initialize(hidden_size, visible_size)
##======================================================================
## STEP 2: Implement sparseAutoencoderCost
#
# You can implement all of the components (squared error cost, weight decay term,
# sparsity penalty) in the cost function at once, but it may be easier to do
# it step-by-step and run gradient checking (see STEP 3) after each step. We
# suggest implementing the sparseAutoencoderCost function using the following steps:
#
# (a) Implement forward propagation in your neural network, and implement the
# squared error term of the cost function. Implement backpropagation to
# compute the derivatives. Then (using lambda=beta=0), run Gradient Checking
# to verify that the calculations corresponding to the squared error cost
# term are correct.
#
#
# This loads our training data from the MNIST database files.
train_images = load_MNIST.load_MNIST_images('data/mnist/train-images-idx3-ubyte')
train_labels = load_MNIST.load_MNIST_labels('data/mnist/train-labels-idx1-ubyte')
##======================================================================
## STEP 2: Train the first sparse autoencoder
# This trains the first sparse autoencoder on the unlabelled STL training
# images.
# If you've correctly implemented sparseAutoencoderCost.m, you don't need
# to change anything here.
# Randomly initialize the parameters
sae1_theta = sparse_autoencoder.initialize(hidden_size_L1, input_size)
J = lambda x: sparse_autoencoder.sparse_autoencoder_cost(x, input_size, hidden_size_L1,
lambda_, sparsity_param,
beta, train_images)
options_ = {'maxiter': 400, 'disp': True}
result = scipy.optimize.minimize(J, sae1_theta, method='L-BFGS-B', jac=True, options=options_)
sae1_opt_theta = result.x
print result
##======================================================================
## STEP 3: Train the second sparse autoencoder
# This trains the second sparse autoencoder on the first autoencoder
# featurse.
train_labels = labels[train_index]
test_data = images[:, test_index]
test_labels = labels[test_index]
print '# examples in unlabeled set: {0:d}\n'.format(unlabeled_data.shape[1])
print '# examples in supervised training set: {0:d}\n'.format(train_data.shape[1])
print '# examples in supervised testing set: {0:d}\n'.format(test_data.shape[1])
## ======================================================================
# STEP 2: Train the sparse autoencoder
# This trains the sparse autoencoder on the unlabeled training
# images.
# Randomly initialize the parameters
theta = sparse_autoencoder.initialize(hidden_size, input_size)
J = lambda x: sparse_autoencoder.sparse_autoencoder_cost(x, input_size, hidden_size,
lambda_, sparsity_param,
beta, unlabeled_data)
options_ = {'maxiter': 400, 'disp': True}
result = scipy.optimize.minimize(J, theta, method='L-BFGS-B', jac=True, options=options_)
opt_theta = result.x
print result
# Visualize the weights
W1 = opt_theta[0:hidden_size * input_size].reshape(hidden_size, input_size).transpose()
display_network.display_network(W1)
