Skip to content

Update code to support Python 3 to follow Chapter 5 http://neuralnetworksanddeeplearning.com/ examples #101

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
+15 −17
Open

Update code to support Python 3 to follow Chapter 5 http://neuralnetworksanddeeplearning.com/ examples #101

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 7 additions & 7 deletions src/mnist_loader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@

#### Libraries
# Standard library
import cPickle
import pickle
import gzip

# Third-party libraries
Expand Down Expand Up @@ -39,11 +39,11 @@ def load_data():
That's done in the wrapper function ``load_data_wrapper()``, see
below.
"""
f = gzip.open('../data/mnist.pkl.gz', 'rb')
training_data, validation_data, test_data = cPickle.load(f)
f.close()
with gzip.open('../data/mnist.pkl.gz', 'rb') as f:
training_data, validation_data, test_data = pickle.load(f, encoding='latin1')
return (training_data, validation_data, test_data)


def load_data_wrapper():
"""Return a tuple containing ``(training_data, validation_data,
test_data)``. Based on ``load_data``, but the format is more
Expand All @@ -68,11 +68,11 @@ def load_data_wrapper():
tr_d, va_d, te_d = load_data()
training_inputs = [np.reshape(x, (784, 1)) for x in tr_d[0]]
training_results = [vectorized_result(y) for y in tr_d[1]]
training_data = zip(training_inputs, training_results)
training_data = list(zip(training_inputs, training_results))
validation_inputs = [np.reshape(x, (784, 1)) for x in va_d[0]]
validation_data = zip(validation_inputs, va_d[1])
validation_data = list(zip(validation_inputs, va_d[1]))
test_inputs = [np.reshape(x, (784, 1)) for x in te_d[0]]
test_data = zip(test_inputs, te_d[1])
test_data = list(zip(test_inputs, te_d[1]))
return (training_data, validation_data, test_data)

def vectorized_result(j):
Expand Down
18 changes: 8 additions & 10 deletions src/network2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,33 +156,31 @@ def SGD(self, training_data, epochs, mini_batch_size, eta,
n = len(training_data)
evaluation_cost, evaluation_accuracy = [], []
training_cost, training_accuracy = [], []
for j in xrange(epochs):
for j in range(epochs):
random.shuffle(training_data)
mini_batches = [
training_data[k:k+mini_batch_size]
for k in xrange(0, n, mini_batch_size)]
for k in range(0, n, mini_batch_size)]
for mini_batch in mini_batches:
self.update_mini_batch(
mini_batch, eta, lmbda, len(training_data))
print "Epoch %s training complete" % j
print("Epoch %s training complete" % j)
if monitor_training_cost:
cost = self.total_cost(training_data, lmbda)
training_cost.append(cost)
print "Cost on training data: {}".format(cost)
print("Cost on training data: {}".format(cost))
if monitor_training_accuracy:
accuracy = self.accuracy(training_data, convert=True)
training_accuracy.append(accuracy)
print "Accuracy on training data: {} / {}".format(
accuracy, n)
print("Accuracy on training data: {} / {}".format(accuracy, n))
if monitor_evaluation_cost:
cost = self.total_cost(evaluation_data, lmbda, convert=True)
evaluation_cost.append(cost)
print "Cost on evaluation data: {}".format(cost)
print("Cost on evaluation data: {}".format(cost))
if monitor_evaluation_accuracy:
accuracy = self.accuracy(evaluation_data)
evaluation_accuracy.append(accuracy)
print "Accuracy on evaluation data: {} / {}".format(
self.accuracy(evaluation_data), n_data)
print("Accuracy on evaluation data: {} / {}".format(self.accuracy(evaluation_data), n_data))
print
return evaluation_cost, evaluation_accuracy, \
training_cost, training_accuracy
Expand Down Expand Up @@ -232,7 +230,7 @@ def backprop(self, x, y):
# second-last layer, and so on. It's a renumbering of the
# scheme in the book, used here to take advantage of the fact
# that Python can use negative indices in lists.
for l in xrange(2, self.num_layers):
for l in range(2, self.num_layers):
z = zs[-l]
sp = sigmoid_prime(z)
delta = np.dot(self.weights[-l+1].transpose(), delta) * sp
Expand Down