input_data = np.random.randn(input_size, 100)
labels = np.random.randint(num_classes, size=100)
else:
input_size = 28 * 28
input_data = images
# Randomly initialise theta
theta = 0.005 * np.random.randn(num_classes * input_size)
##======================================================================
## STEP 2: Implement softmaxCost
#
# Implement softmaxCost in softmaxCost.m.
(cost, grad) = softmax.softmax_cost(theta, num_classes, input_size, lambda_, input_data, labels)
##======================================================================
## STEP 3: Gradient checking
#
# As with any learning algorithm, you should always check that your
# gradients are correct before learning the parameters.
#
if debug:
J = lambda x: softmax.softmax_cost(x, num_classes, input_size, lambda_, input_data, labels)
num_grad = gradient.compute_gradient(J, theta)
# Use this to visually compare the gradients side by side
print num_grad, grad
# Here, we create synthetic dataset using random data for testing
debug = False
if debug:
input_size = 8 * 8
input_data = np.random.randn(input_size, 100)
labels = np.random.randint(n_classes, size=100)
# Randomly initialise theta
theta = 0.005 * np.random.randn(n_classes * input_size)
"""
STEP 2: Implement softmax_cost
Implement softmax_cost in softmax_cost.py.
"""
cost, grad = softmax_cost(theta, n_classes, input_size, lambda_, input_data,
labels)
"""
STEP 3: Gradient checking
As with any learning algorithm, you should always check that your
gradients are correct before learning the parameters.
"""
if debug:
# Now we can use it to check your cost function and derivative calculations
# for the sparse autoencoder.
J = lambda theta: softmax_cost(theta, n_classes, input_size, lambda_,
input_data, labels)[0]
numgrad = compute_numerical_gradient(J, theta)
debug = False
if debug:
input_size = 8 * 8
input_data = np.random.randn(input_size, 100)
labels = np.random.randint(n_classes, size=100)
# Randomly initialise theta
theta = 0.005 * np.random.randn(n_classes * input_size)
"""
STEP 2: Implement softmax_cost
Implement softmax_cost in softmax_cost.py.
"""
cost, grad = softmax_cost(theta, n_classes, input_size, lambda_, input_data, labels)
"""
STEP 3: Gradient checking
As with any learning algorithm, you should always check that your
gradients are correct before learning the parameters.
"""
if debug:
# Now we can use it to check your cost function and derivative calculations
# for the sparse autoencoder.
J = lambda theta : softmax_cost(theta, n_classes, input_size, lambda_, input_data, labels)[0]
numgrad = compute_numerical_gradient(J, theta)