def test_perceptron():
Graph().as_default()
x = Placeholder()
w = Variable([1, 1])
b = Variable(0)
p = sigmoid(add(matmul(w, x), b))
session = Session()
output = session.run(p, {x: [3, 2]})
print(output)
def test_train():
red_points = np.random.randn(50, 2) - 2 * np.ones((50, 2))
blue_points = np.random.randn(50, 2) + 2 * np.ones((50, 2))
Graph().as_default()
X = Placeholder()
c = Placeholder()
# Initialize weights randomly
W = Variable(np.random.randn(2, 2))
b = Variable(np.random.randn(2))
# Build perceptron
p = softmax(add(matmul(X, W), b))
# Build cross-entropy loss
J = negative(reduce_sum(reduce_sum(multiply(c, log(p)), axis=1)))
# Build minimization op
minimization_op = GradientDescentOptimizer(learning_rate=0.01).minimize(J)
# Build placeholder inputs
feed_dict = {
X: np.concatenate((blue_points, red_points)),
c: [[1, 0]] * len(blue_points) + [[0, 1]] * len(red_points)
}
# Create session
session = Session()
# Perform 100 gradient descent steps
for step in range(100):
J_value = session.run(J, feed_dict)
if step % 10 == 0:
print("Step:", step, " Loss:", J_value)
session.run(minimization_op, feed_dict)
# Print final result
W_value = session.run(W)
print("Weight matrix:\n", W_value)
b_value = session.run(b)
print("Bias:\n", b_value)
def test_perceptron_loss():
red_points = np.random.randn(50, 2) - 2 * np.ones((50, 2))
blue_points = np.random.randn(50, 2) + 2 * np.ones((50, 2))
Graph().as_default()
X = Placeholder()
c = Placeholder()
W = Variable([[1, -1], [1, -1]])
b = Variable([0, 0])
p = softmax(add(matmul(X, W), b))
J = negative(reduce_sum(reduce_sum(multiply(c, log(p)), axis=1)))
session = Session()
print(
session.run(
J, {
X: np.concatenate((blue_points, red_points)),
c: [[1, 0]] * len(blue_points) + [[0, 1]] * len(red_points)
}))
def test_compute_graph():
Graph().as_default()
A = Variable([[1, 0], [0, -1]])
b = Variable([1, 1])
x = Placeholder()
y = matmul(A, x)
z = add(y, b)
session = Session()
output = session.run(z, {x: [1, 2]})
print(output)
#!/usr/bin/env python # -*- coding: utf-8 -*- """ An example that builds the graph which performs the following transformation: (1 0) (1) z = (0 -1)* x + (1) """ from graph import Graph from graph import Variable from graph import Placeholder from operations import matmul from operations import add # Create a new graph Graph().as_default() # Create variables A = Variable([[1, 0], [0, -1]]) b = Variable([1, 1]) # Create placeholder x = Placeholder() # Create hidden node y y = matmul(A, x) # Create output node z z = add(y, b)
from graph import Placeholder from operations import matmul from operations import add from operations import sigmoid from operations import softmax from operations import negative from operations import log from operations import reduce_sum from operations import multiply from session import Session import numpy as np # Create a new graph Graph().as_default() X = Placeholder() c = Placeholder() # Create a weight matrix for 2 outout classes: # One with a weight vector (1, 1) for blue and one with a # weight vector (-1, -1) for red W = Variable([[1, -1], [1, -1]]) b = Variable([0, 0]) p = softmax(add(matmul(X, W), b)) # Cross-entropy loss J = negative(reduce_sum(reduce_sum(multiply(c, log(p)), axis=1))) # Create red points centered at (-2, -2) red_points = np.random.randn(50, 2) - 2 * np.ones((50, 2))