hadifar

mnist = tf.keras.datasets.mnist

(x_train, y_train), (x_test, y_test) = mnist.load_data()

# some reshaping here...

X = tf.placeholder(tf.float32, [None, 784], name="X")
Y_truth = tf.placeholder(tf.float32, [None, 10], name="Y")

# define model, loss, and optimizer

hadifar

dataset = tf.data.TextLineDataset("file.txt")
for line in dataset:
    print(line)

hadifar

> TypeError: 'TextLineDataset' object is not iterable

or 

> RuntimeError: dataset.__iter__() is only supported when eager execution is enabled.

hadifar

print(type(dataset))
>>> <class 'tensorflow.python.data.ops.readers.TextLineDataset'>

hadifar

import tensorflow as tf

dataset = tf.data.TextLineDataset("file.txt")
iterator = dataset.make_one_shot_iterator()
next_element = iterator.get_next()

with tf.Session() as sess:
    print(sess.run(next_element))
    print(sess.run(next_element))
    print(sess.run(next_element))

hadifar

import tensorflow as tf

dataset = tf.data.TextLineDataset("file.txt")
iterator = dataset.make_initializable_iterator()
next_element = iterator.get_next()
init_op = iterator.initializer

with tf.Session() as sess:
    # Initialize the iterator
    sess.run(init_op)

hadifar

import time

import numpy as np
import tensorflow as tf

# Step 1: Read in data
(train_x, train_y), (test_x, test_y) = tf.keras.datasets.mnist.load_data()

m_train = train_x.shape[0]
m_test = test_x.shape[0]

hadifar

import time

import numpy as np
import tensorflow as tf

# Step 1: Read in data
(train_x, train_y), (test_x, test_y) = tf.keras.datasets.mnist.load_data()

m_train = train_x.shape[0]
m_test = test_x.shape[0]

hadifar

# create training Dataset and batch it
train_data = tf.data.Dataset.from_tensor_slices(train)
train_data = train_data.shuffle(10000)  # if you want to shuffle your data
train_data = train_data.batch(128)

# create testing Dataset and batch it
test_data = tf.data.Dataset.from_tensor_slices(test)
test_data = test_data.shuffle(10000)
test_data = test_data.batch(128)

hadifar

# create weights and bias for logistic regression
# w is initialized to random variables with mean of 0, stddev of 0.01
# b is initialized to 0
# shape of w depends on the dimension of X and Y so that Y = tf.matmul(X, w)
# shape of b depends on Y
w = tf.get_variable(name='weight',
                    initializer=tf.truncated_normal(shape=[784, 10], mean=0, stddev=0.01))
b = tf.get_variable(name='bias', initializer=tf.zeros([10]))