- What is Tensorflow
TensorFlow is an open source software library for numerical computation using data flow graphs
TensorFlow programs are usually structured into a construction phase, that assembles a graph, and an execution phase that uses a session to execute ops in the graph
A TF program often has 2 phases:
- Assemble a graph
- Use a session to execute operations in the graph
The main types of tensors (in TF) are:
-
tf.Variable / tf.get_variable
-
tf.constant
-
tf.placeholder
-
Constants are fixed value tensors - not trainable
-
Variables are tensors initialized in a session - trainable
-
Placeholders are tensors of values that are unknown during the graph construction, but passed as input during a session
-
Ops are functions on tensors
import tensorflow as tf
input1 = tf.placeholder(tf.float32)
input2 = tf.placeholder(tf.float32)
output = tf.multiply(input1, input2)
with tf.Session() as sess:
print(sess.run(output, feed_dict={input1: [7.], input2: [2.]}))
Change the indentation of print(sess.run(W)) and see the result
from __future__ import print_function
import tensorflow as tf
import numpy
import matplotlib.pyplot as plt
rng = numpy.random
# Parameters
learning_rate = 0.01
training_epochs = 1000
display_step = 50
# Training Data
train_X = numpy.asarray([3.3,4.4,5.5,6.71,6.93,4.168,9.779,6.182,7.59,2.167,
7.042,10.791,5.313,7.997,5.654,9.27,3.1])
train_Y = numpy.asarray([1.7,2.76,2.09,3.19,1.694,1.573,3.366,2.596,2.53,1.221,
2.827,3.465,1.65,2.904,2.42,2.94,1.3])
n_samples = train_X.shape[0]
# tf Graph Input
X = tf.placeholder("float")
Y = tf.placeholder("float")
# Set model weights
W = tf.Variable(rng.randn(), name="weight")
b = tf.Variable(rng.randn(), name="bias")
# Construct a linear model
pred = tf.add(tf.multiply(X, W), b)
# Mean squared error
cost = tf.reduce_sum(tf.pow(pred-Y, 2))/(2*n_samples)
# Gradient descent
# Note, minimize() knows to modify W and b because Variable objects are trainable=True by default
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)
# Initialize the variables (i.e. assign their default value)
init = tf.global_variables_initializer()
# Start training
with tf.Session() as sess:
# Run the initializer
sess.run(init)
# Fit all training data
for epoch in range(training_epochs):
for (x, y) in zip(train_X, train_Y):
sess.run(optimizer, feed_dict={X: x, Y: y})
print(sess.run(W))import tensorflow as tf
import numpy as np
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
import matplotlib.pyplot as plt
# Import data
data = pd.read_csv('01_data/data_stocks.csv')
# Drop date variable
data = data.drop(['DATE'], 1)
# Dimensions of dataset
n = data.shape[0]
p = data.shape[1]
# Make data a np.array
data = data.values
# Training and test data
train_start = 0
train_end = int(np.floor(0.8*n))
test_start = train_end + 1
test_end = n
data_train = data[np.arange(train_start, train_end), :]
data_test = data[np.arange(test_start, test_end), :]
# Scale data
scaler = MinMaxScaler(feature_range=(-1, 1))
scaler.fit(data_train)
data_train = scaler.transform(data_train)
data_test = scaler.transform(data_test)
# Build X and y
X_train = data_train[:, 1:]
y_train = data_train[:, 0]
X_test = data_test[:, 1:]
y_test = data_test[:, 0]
# Number of stocks in training data
n_stocks = X_train.shape[1]
# Neurons
n_neurons_1 = 1024
n_neurons_2 = 512
n_neurons_3 = 256
n_neurons_4 = 128
# Session
net = tf.InteractiveSession()
# Placeholder
X = tf.placeholder(dtype=tf.float32, shape=[None, n_stocks])
Y = tf.placeholder(dtype=tf.float32, shape=[None])
# Initializers
sigma = 1
weight_initializer = tf.variance_scaling_initializer(mode="fan_avg", distribution="uniform", scale=sigma)
bias_initializer = tf.zeros_initializer()
# Hidden weights
W_hidden_1 = tf.Variable(weight_initializer([n_stocks, n_neurons_1]))
bias_hidden_1 = tf.Variable(bias_initializer([n_neurons_1]))
W_hidden_2 = tf.Variable(weight_initializer([n_neurons_1, n_neurons_2]))
bias_hidden_2 = tf.Variable(bias_initializer([n_neurons_2]))
W_hidden_3 = tf.Variable(weight_initializer([n_neurons_2, n_neurons_3]))
bias_hidden_3 = tf.Variable(bias_initializer([n_neurons_3]))
W_hidden_4 = tf.Variable(weight_initializer([n_neurons_3, n_neurons_4]))
bias_hidden_4 = tf.Variable(bias_initializer([n_neurons_4]))
# Output weights
W_out = tf.Variable(weight_initializer([n_neurons_4, 1]))
bias_out = tf.Variable(bias_initializer([1]))
# Hidden layer
hidden_1 = tf.nn.relu(tf.add(tf.matmul(X, W_hidden_1), bias_hidden_1))
hidden_2 = tf.nn.relu(tf.add(tf.matmul(hidden_1, W_hidden_2), bias_hidden_2))
hidden_3 = tf.nn.relu(tf.add(tf.matmul(hidden_2, W_hidden_3), bias_hidden_3))
hidden_4 = tf.nn.relu(tf.add(tf.matmul(hidden_3, W_hidden_4), bias_hidden_4))
# Output layer (transpose!)
out = tf.transpose(tf.add(tf.matmul(hidden_4, W_out), bias_out))
# Cost function
mse = tf.reduce_mean(tf.squared_difference(out, Y))
# Optimizer
opt = tf.train.AdamOptimizer().minimize(mse)
# Init
net.run(tf.global_variables_initializer())
# Setup plot
plt.ion()
fig = plt.figure()
ax1 = fig.add_subplot(111)
line1, = ax1.plot(y_test)
line2, = ax1.plot(y_test * 0.5)
plt.show()
# Fit neural net
batch_size = 256
mse_train = []
mse_test = []
# Run
epochs = 10
for e in range(epochs):
# Shuffle training data
shuffle_indices = np.random.permutation(np.arange(len(y_train)))
X_train = X_train[shuffle_indices]
y_train = y_train[shuffle_indices]
# Minibatch training
for i in range(0, len(y_train) // batch_size):
start = i * batch_size
batch_x = X_train[start:start + batch_size]
batch_y = y_train[start:start + batch_size]
# Run optimizer with batch
net.run(opt, feed_dict={X: batch_x, Y: batch_y})
# Show progress
if np.mod(i, 50) == 0:
# MSE train and test
mse_train.append(net.run(mse, feed_dict={X: X_train, Y: y_train}))
mse_test.append(net.run(mse, feed_dict={X: X_test, Y: y_test}))
print('MSE Train: ', mse_train[-1])
print('MSE Test: ', mse_test[-1])
# Prediction
pred = net.run(out, feed_dict={X: X_test})
line2.set_ydata(pred)
plt.title('Epoch ' + str(e) + ', Batch ' + str(i))
plt.pause(0.01)import tensorflow as tf
a, b = tf.while_loop(lambda x, y: x < 30, lambda x, y: (x * 3, y * 2), (2, 3))
# Run the while loop and get the resulting values.
with tf.Session() as sess:
print(sess.run([a, b]))
with tf.device("/gpu:0"):
# Setup operations
with tf.Session() as sess:
# Run your code
import tensorflow as tf
# Zeros matrix
num = tf.get_variable('num', shape=[5, 3], initializer=tf.zeros_initializer(), dtype=tf.float32)
# Looping variable
i = tf.constant(0, dtype=tf.int32)
def body(i, num, j):
# Update values
updates = tf.ones([1, 3], dtype=tf.float32)
for i in range(sess.run(tf.add(i, j))):
num = tf.scatter_nd_update(num, [[i]], updates)
return num
sess = tf.Session()
sess.run(tf.global_variables_initializer())
print(sess.run(body(i, num, 2)))import tensorflow as tf
a = tf.Variable(initial_value=tf.constant([1, 2, 3, 4, 5, 6, 7, 8]))
indices = tf.constant([[4], [3], [1], [7]])
updates = tf.constant([9, 10, 11, 12])
update = tf.scatter_nd_update(a, indices, updates)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
print(sess.run(update))