y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
# loss
cross_entropy = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
train_step = tf.train.AdamOptimizer(5e-3).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# 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)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(200):
print(i)
batch = mnist.train.next_batch(100)
if i % 5 == 0:
train_accuracy = accuracy.eval(feed_dict={
x: batch[0],
y_: batch[1],
keep_prob: 1.0
})
print('step %d, trainning accuracy %g' % (i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
ans = accuracy.eval(feed_dict={
x: mnist.test.images,
""" import your model here """
import tensorwolf as tf
""" your model should support the following code """
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
init = tf.global_variables_initializer()
sess.run(init)
ans = sess.run(linear_model, {x: [1, 2, 3, 4]})
assert np.array_equal(ans, [2, 2.5, 3, 3.5])