本文整理汇总了Python中NeuralNetwork.NeuralNetwork.gradient_descent方法的典型用法代码示例。如果您正苦于以下问题：Python NeuralNetwork.gradient_descent方法的具体用法？Python NeuralNetwork.gradient_descent怎么用？Python NeuralNetwork.gradient_descent使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类NeuralNetwork.NeuralNetwork的用法示例。
在下文中一共展示了NeuralNetwork.gradient_descent方法的1个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: main
# 需要导入模块: from NeuralNetwork import NeuralNetwork [as 别名]
# 或者: from NeuralNetwork.NeuralNetwork import gradient_descent [as 别名]
def main():
if len(sys.argv) != 3:
print "USAGE: python DigitClassifier" \
"<path_to_training_file> <path_to_testing_file>"
sys.exit(-1)
training_data = None
validation_data = None
testing_data = None
# load training file
print "Loading training data from '" + sys.argv[1] + "'..."
with open(sys.argv[1], 'rb') as f:
# skip headings
next(f)
X = []
Y = []
for line in f:
line = line.strip().split(',', 1)
Y.append(vectorize_digit(int(line[0])))
X.append(line[1].split(','))
# convert X into numpys float32 representation
X = np.array(X).astype(np.float32)
# normalize pixel values to lie between 0 - 1
# performance is very bad without normalization
X *= 1.0 / 255.0
X = [np.reshape(i, (784, 1)) for i in X]
# split point
N = int(len(X) * 0.2)
# split the data into 80-20
x = X[:N]
X = X[N:]
y = [de_vectorize(i) for i in Y[:N]]
Y = Y[N:]
training_data = zip(X, Y)
validation_data = zip(x, y)
print "Data Loaded."
print "Generating Neural Network..."
input_layer_neurons = 784
hidden_layer_neurons = [30]
output_layer_neurons = 10
epochs = 30
batch_size = 10
learning_rate = 3.0
net = NeuralNetwork([input_layer_neurons] +
hidden_layer_neurons + [output_layer_neurons])
print "Network Generated..."
print "\t Input Layer neuron count: " + str(input_layer_neurons)
print "\t Hidden Layer Count: " + str(len(hidden_layer_neurons))
for i in xrange(len(hidden_layer_neurons)):
print "\t\tHidden Layer " + str(i + 1) + " neuron count: "\
+ str(hidden_layer_neurons[i])
print "\t Output Layer neuron count: " + str(output_layer_neurons)
print "\nTraining for " + str(epochs) + " epochs..."
net.gradient_descent(training_data, epochs, batch_size,
learning_rate, validation_data)
# load training file
print "Loading testing data from '" + sys.argv[2] + "'..."
with open(sys.argv[2], 'rb') as f:
# skip headings
next(f)
X = []
for line in f:
X.append(line.split(','))
X = np.array(X).astype(np.float32)
X *= 1.0 / 255.0
X = [np.reshape(i, (784, 1)) for i in X]
testing_data = X
# get the classifier predictions
predictions = net.classify(testing_data)
print predictions
return