1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
|
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "U9i2Dsh-ziXr"
},
"source": [
"# Eager Execution Tutorial: Importing Data\n",
"\n",
"This notebook demonstrates the use of the [`tf.contrib.data.Dataset` API](https://www.tensorflow.org/programmers_guide/datasets) to build pipelines to feed data to your program. It covers:\n",
"\n",
"* Creating a `Dataset`.\n",
"* Iteration over a `Dataset` with eager execution enabled.\n",
"\n",
"We recommend using the `Dataset`s API for building performant, complex input pipelines from simple, re-usable pieces that will feed your model's training or evaluation loops.\n",
"\n",
"If you're familiar with TensorFlow graphs, the API for constructing the `Dataset` object remains exactly the same when eager execution is enabled, but the process of iterating over elements of the dataset is slightly different. You will use a Pythonic `Iterator()` class instead of using `make_one_shot_iterator()` and `get_next()`. As a result, the discussion on iterators in the [Programmer's Guide](https://www.tensorflow.org/programmers_guide/datasets) is not relevant when eager execution is enabled."
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "z1JcS5iBXMRO"
},
"source": [
"# Setup: Enable eager execution\n"
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"cellView": "code",
"colab": {
"autoexec": {
"startup": false,
"wait_interval": 0
}
},
"colab_type": "code",
"id": "RlIWhyeLoYnG"
},
"outputs": [],
"source": [
"# Import TensorFlow.\n",
"import tensorflow as tf\n",
"\n",
"# Import TensorFlow eager execution support (subject to future changes).\n",
"import tensorflow.contrib.eager as tfe\n",
"\n",
"# Enable eager execution\n",
"tfe.enable_eager_execution()"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "H9UySOPLXdaw"
},
"source": [
"# Step 1: Create a source `Dataset`\n",
"\n",
"Create a _source_ dataset using one of the factory functions like [`Dataset.from_tensors`](https://www.tensorflow.org/api_docs/python/tf/contrib/data/Dataset#from_tensors), [`Dataset.from_tensor_slices`](https://www.tensorflow.org/api_docs/python/tf/contrib/data/Dataset#from_tensor_slices) or using objects that read from files like [`TextLineDataset`](https://www.tensorflow.org/api_docs/python/tf/contrib/data/TextLineDataset) or [`TFRecordDataset`](https://www.tensorflow.org/api_docs/python/tf/contrib/data/TFRecordDataset). See the [Programmer's Guide](https://www.google.com/url?sa=D\u0026q=https%3A%2F%2Fwww.tensorflow.org%2Fprogrammers_guide%2Fdatasets%23reading_input_data) for more information."
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"cellView": "code",
"colab": {
"autoexec": {
"startup": false,
"wait_interval": 0
}
},
"colab_type": "code",
"id": "WPTUfGq6kJ5w"
},
"outputs": [],
"source": [
"ds_tensors = tf.contrib.data.Dataset.from_tensor_slices([1, 2, 3, 4, 5, 6])\n",
"\n",
"# Create a CSV file\n",
"import tempfile\n",
"_, filename = tempfile.mkstemp()\n",
"with open(filename, 'w') as f:\n",
" f.write(\"\"\"Line 1\n",
"Line 2\n",
"Line 3\n",
" \"\"\")\n",
"ds_file = tf.contrib.data.TextLineDataset(filename)\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "twBfWd5xyu_d"
},
"source": [
"# Step 2: Apply transformations\n",
"\n",
"Use the transformations functions like [`map`](https://www.tensorflow.org/api_docs/python/tf/contrib/data/Dataset#map), [`batch`](https://www.tensorflow.org/api_docs/python/tf/contrib/data/Dataset#batch), [`shuffle`](https://www.tensorflow.org/api_docs/python/tf/contrib/data/Dataset#shuffle) etc. to apply transformations to the records of the dataset. See the [API documentation for `tf.contrib.data.Dataset`](https://www.tensorflow.org/api_docs/python/tf/contrib/data/Dataset) for details."
]
},
{
"cell_type": "code",
"execution_count": 0,
"metadata": {
"cellView": "code",
"colab": {
"autoexec": {
"startup": false,
"wait_interval": 0
}
},
"colab_type": "code",
"id": "ngUe237Wt48W"
},
"outputs": [],
"source": [
"ds_tensors = ds_tensors.map(tf.square).shuffle(2).batch(2)\n",
"ds_file = ds_file.batch(2)"
]
},
{
"cell_type": "markdown",
"metadata": {
"colab_type": "text",
"id": "IDY4WsYRhP81"
},
"source": [
"# Step 3: Iterate\n",
"\n",
"Use `tfe.Iterator` on the `Dataset` object to get a Python iterator over the contents of the dataset.\n",
"\n",
"If you're familiar with the use of `Dataset`s in TensorFlow graphs, note that this process of iteration is different. Here there are no calls to `Dataset.make_one_shot_iterator()` and no `get_next()` calls."
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"colab": {
"autoexec": {
"startup": false,
"wait_interval": 0
},
"height": 153,
"output_extras": [
{
"item_id": 1
}
]
},
"colab_type": "code",
"executionInfo": {
"elapsed": 201,
"status": "ok",
"timestamp": 1505952405928,
"user": {
"displayName": "",
"photoUrl": "",
"userId": ""
},
"user_tz": 420
},
"id": "lCUWzso6mbqR",
"outputId": "ec027d30-96c6-4ea4-9ee1-ef74ec1ae29a"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Elements of ds_tensors:\n",
"tf.Tensor([4 9], shape=(2,), dtype=int32)\n",
"tf.Tensor([16 25], shape=(2,), dtype=int32)\n",
"tf.Tensor([36 1], shape=(2,), dtype=int32)\n",
"\n",
"Elements in ds_file:\n",
"tf.Tensor(['Line 1' 'Line 2'], shape=(2,), dtype=string)\n",
"tf.Tensor(['Line 3' ' '], shape=(2,), dtype=string)\n"
]
}
],
"source": [
"print('Elements of ds_tensors:')\n",
"for x in tfe.Iterator(ds_tensors):\n",
" print(x)\n",
"\n",
"print('\\nElements in ds_file:')\n",
"for x in tfe.Iterator(ds_file):\n",
" print(x)"
]
}
],
"metadata": {
"colab": {
"default_view": {},
"last_runtime": {
"build_target": "",
"kind": "local"
},
"name": "Eager Execution Tutorial: Importing Data",
"provenance": [],
"version": "0.3.2",
"views": {}
}
},
"nbformat": 4,
"nbformat_minor": 0
}
|
