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.
# If you've correctly implemented sparseAutoencoderCost.m, you don't need
# to change anything here.
sae1_features = sparse_autoencoder.sparse_autoencoder(sae1_opt_theta,
hidden_size_L1,
input_size, train_images)
# Randomly initialize the parameters
sae2_theta = sparse_autoencoder.initialize(hidden_size_L2, hidden_size_L1)
J = lambda x: sparse_autoencoder.sparse_autoencoder_cost(
x, hidden_size_L1, hidden_size_L2, lambda_, sparsity_param, beta,
sae1_features)
options_ = {'maxiter': 400, 'disp': True}
result = scipy.optimize.minimize(J,
sae2_theta,
method='L-BFGS-B',
jac=True,
image_num = np.random.randint(0, 8)
image_row = np.random.randint(0, image_dim - patch_dim + 1)
image_col = np.random.randint(0, image_dim - patch_dim + 1)
patch = conv_images[image_row:image_row + patch_dim,
image_col:image_col + patch_dim, :, image_num]
patch = np.concatenate(
(patch[:, :, 0].flatten(), patch[:, :,
1].flatten(), patch[:, :,
2].flatten()))
patch = np.reshape(patch, (patch.size, 1))
patch = patch - np.tile(patch_mean, (patch.shape[1], 1)).transpose()
patch = zca_white.dot(patch)
features = sparse_autoencoder.sparse_autoencoder(opt_theta, hidden_size,
visible_size, patch)
if abs(features[feature_num, 0] -
convolved_features[feature_num, image_num, image_row,
image_col]) > 1e-9:
print('Convolved feature does not match activation from autoencoder')
print('Feature Number :', feature_num)
print('Image Number :', image_num)
print('Image Row :', image_row)
print('Image Column :', image_col)
print('Convolved feature :',
convolved_features[feature_num, image_num, image_row, image_col])
print('Sparse AE feature :', features[feature_num, 0])
sys.exit(
"Convolved feature does not match activation from autoencoder. Exiting..."
)
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)
##======================================================================
## STEP 3: Extract Features from the Supervised Dataset
#
# You need to complete the code in feedForwardAutoencoder.m so that the
# following command will extract features from the data.
train_features = sparse_autoencoder.sparse_autoencoder(opt_theta, hidden_size,
input_size, train_data)
test_features = sparse_autoencoder.sparse_autoencoder(opt_theta, hidden_size,
input_size, test_data)
##======================================================================
## STEP 4: Train the softmax classifier
lambda_ = 1e-4
options_ = {'maxiter': 400, 'disp': True}
opt_theta, input_size, num_classes = softmax.softmax_train(hidden_size, num_labels,
lambda_, train_features,
train_labels, options_)
##======================================================================
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.
# If you've correctly implemented sparseAutoencoderCost.m, you don't need
# to change anything here.
sae1_features = sparse_autoencoder.sparse_autoencoder(sae1_opt_theta, hidden_size_L1,
input_size, train_images)
# Randomly initialize the parameters
sae2_theta = sparse_autoencoder.initialize(hidden_size_L2, hidden_size_L1)
J = lambda x: sparse_autoencoder.sparse_autoencoder_cost(x, hidden_size_L1, hidden_size_L2,
lambda_, sparsity_param,
beta, sae1_features)
options_ = {'maxiter': 400, 'disp': True}
result = scipy.optimize.minimize(J, sae2_theta, method='L-BFGS-B', jac=True, options=options_)
sae2_opt_theta = result.x
print result
# For 1000 random points
for i in range(1000):
feature_num = np.random.randint(0, hidden_size)
image_num = np.random.randint(0, 8)
image_row = np.random.randint(0, image_dim - patch_dim + 1)
image_col = np.random.randint(0, image_dim - patch_dim + 1)
patch = conv_images[image_row:image_row + patch_dim, image_col:image_col + patch_dim, :, image_num]
patch = np.concatenate((patch[:, :, 0].flatten(), patch[:, :, 1].flatten(), patch[:, :, 2].flatten()))
patch = np.reshape(patch, (patch.size, 1))
patch = patch - np.tile(patch_mean, (patch.shape[1], 1)).transpose()
patch = zca_white.dot(patch)
features = sparse_autoencoder.sparse_autoencoder(opt_theta, hidden_size, visible_size, patch)
if abs(features[feature_num, 0] - convolved_features[feature_num, image_num, image_row, image_col]) > 1e-9:
print 'Convolved feature does not match activation from autoencoder'
print 'Feature Number :', feature_num
print 'Image Number :', image_num
print 'Image Row :', image_row
print 'Image Column :', image_col
print 'Convolved feature :', convolved_features[feature_num, image_num, image_row, image_col]
print 'Sparse AE feature :', features[feature_num, 0]
sys.exit("Convolved feature does not match activation from autoencoder. Exiting...")
print 'Congratulations! Your convolution code passed the test.'
## STEP 2c: Implement pooling
# Implement pooling in the function cnnPool in cnnPool.m