x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x, W) + b)
# define loss and optimizer
y_ = tf.placeholder(tf.float32, [None, 10])
cross_entropy = tf.reduce_mean(
-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
W_grad = tf.gradients(cross_entropy, [W])[0]
train_step = tf.assign(W, W - 0.5 * W_grad)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
# get the mnist dataset (use tensorflow here)
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
# train
for _ in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
# eval
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
ans = sess.run(accuracy,
import numpy as np
sess = tf.Session()
# linear model
W = tf.Variable([.5], dtype=tf.float32)
b = tf.Variable([1.5], dtype=tf.float32)
x = tf.placeholder(tf.float32)
linear_model = W * x + b
# define error
y = tf.placeholder(tf.float32)
error = tf.reduce_sum(linear_model - y)
# run init
init = tf.global_variables_initializer()
sess.run(init)
# calc error
feed = {x: [1, 2, 3, 4], y: [0, -1, -2, -3]}
# assign
fixW = tf.assign(W, [-1.0])
fixb = tf.assign(b, [1.])
sess.run([fixW, fixb])
ans = sess.run(error, feed)
assert np.equal(ans, 0)
