While reading TensorFlow Introduction, make a note of what you have investigated.
If you connect all the codes written in Introduction, it will be as follows.
import tensorflow as tf
import numpy as np
# Create 100 phony x, y data points in NumPy, y = x * 0.1 + 0.3
x_data = np.random.rand(100).astype(np.float32)
y_data = x_data * 0.1 + 0.3
# Try to find values for W and b that compute y_data = W * x_data + b
# (We know that W should be 0.1 and b 0.3, but TensorFlow will
# figure that out for us.)
W = tf.Variable(tf.random_uniform([1], -1.0, 1.0))
b = tf.Variable(tf.zeros([1]))
y = W * x_data + b
# Minimize the mean squared errors.
loss = tf.reduce_mean(tf.square(y - y_data))
optimizer = tf.train.GradientDescentOptimizer(0.5)
train = optimizer.minimize(loss)
# Before starting, initialize the variables. We will 'run' this first.
init = tf.global_variables_initializer()
# Launch the graph.
sess = tf.Session()
sess.run(init)
# Fit the line.
for step in range(201):
sess.run(train)
if step % 20 == 0:
print(step, sess.run(W), sess.run(b))
# Learns best fit is W: [0.1], b: [0.3]
https://www.tensorflow.org/get_started/
Broadcasting operation
y = W * x_data + b
print(type(W)) # <class 'tensorflow.python.ops.variables.Variable'>
print(type(b)) # <class 'tensorflow.python.ops.variables.Variable'>
print(type(x_data)) # <class 'numpy.ndarray'>
print(type(y)) # <class 'tensorflow.python.framework.ops.Tensor'>
I'm scared to multiply tf.Variable and numpy.ndarray here, but Tensorflow seems to support numpy-style broadcasts. For more information, see Stackoverflow and Glossary / glossary) is a good place to look.
Convert numpy to tensor
You can pass numpy.ndarray objects directly to tf.Variable and tf.constant.
import tensorflow as tf
import numpy as np
a = tf.Variable(np.arange(10))
c = (np.zeros(10))
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
print(sess.run(a)) # [0 1 2 3 4 5 6 7 8 9]
print(sess.run(c)) # [ 0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]
At Quora, TensorFlow team at Google
Yes, the TensorFlow API is designed to make it easy to convert data to and from NumPy arrays:
It states.
Convert tensor to numpy
To convert from tensor to numpy, you can use Session.run or eval.
import tensorflow as tf
import numpy as np
x = tf.zeros([10])
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
print(type(sess.run(x)))
print(type(x.eval()))
As far as the API documentation is concerned, x.eval () is syntactic sugar for sess.run (x). It looks good to think.
Recommended Posts