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
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
|
// Protocol messages for describing input data Examples for machine learning
// model training or inference.
syntax = "proto3";
import "tensorflow/core/example/feature.proto";
option cc_enable_arenas = true;
option java_outer_classname = "ExampleProtos";
option java_multiple_files = true;
option java_package = "org.tensorflow.example";
option go_package = "github.com/tensorflow/tensorflow/tensorflow/go/core/example";
package tensorflow;
// An Example is a mostly-normalized data format for storing data for
// training and inference. It contains a key-value store (features); where
// each key (string) maps to a Feature message (which is oneof packed BytesList,
// FloatList, or Int64List). This flexible and compact format allows the
// storage of large amounts of typed data, but requires that the data shape
// and use be determined by the configuration files and parsers that are used to
// read and write this format. That is, the Example is mostly *not* a
// self-describing format. In TensorFlow, Examples are read in row-major
// format, so any configuration that describes data with rank-2 or above
// should keep this in mind. For example, to store an M x N matrix of Bytes,
// the BytesList must contain M*N bytes, with M rows of N contiguous values
// each. That is, the BytesList value must store the matrix as:
// .... row 0 .... .... row 1 .... // ........... // ... row M-1 ....
//
// An Example for a movie recommendation application:
// features {
// feature {
// key: "age"
// value { float_list {
// value: 29.0
// }}
// }
// feature {
// key: "movie"
// value { bytes_list {
// value: "The Shawshank Redemption"
// value: "Fight Club"
// }}
// }
// feature {
// key: "movie_ratings"
// value { float_list {
// value: 9.0
// value: 9.7
// }}
// }
// feature {
// key: "suggestion"
// value { bytes_list {
// value: "Inception"
// }}
// }
// # Note that this feature exists to be used as a label in training.
// # E.g., if training a logistic regression model to predict purchase
// # probability in our learning tool we would set the label feature to
// # "suggestion_purchased".
// feature {
// key: "suggestion_purchased"
// value { float_list {
// value: 1.0
// }}
// }
// # Similar to "suggestion_purchased" above this feature exists to be used
// # as a label in training.
// # E.g., if training a linear regression model to predict purchase
// # price in our learning tool we would set the label feature to
// # "purchase_price".
// feature {
// key: "purchase_price"
// value { float_list {
// value: 9.99
// }}
// }
// }
//
// A conformant Example data set obeys the following conventions:
// - If a Feature K exists in one example with data type T, it must be of
// type T in all other examples when present. It may be omitted.
// - The number of instances of Feature K list data may vary across examples,
// depending on the requirements of the model.
// - If a Feature K doesn't exist in an example, a K-specific default will be
// used, if configured.
// - If a Feature K exists in an example but contains no items, the intent
// is considered to be an empty tensor and no default will be used.
message Example {
Features features = 1;
};
// A SequenceExample is an Example representing one or more sequences, and
// some context. The context contains features which apply to the entire
// example. The feature_lists contain a key, value map where each key is
// associated with a repeated set of Features (a FeatureList).
// A FeatureList thus represents the values of a feature identified by its key
// over time / frames.
//
// Below is a SequenceExample for a movie recommendation application recording a
// sequence of ratings by a user. The time-independent features ("locale",
// "age", "favorites") describing the user are part of the context. The sequence
// of movies the user rated are part of the feature_lists. For each movie in the
// sequence we have information on its name and actors and the user's rating.
// This information is recorded in three separate feature_list(s).
// In the example below there are only two movies. All three feature_list(s),
// namely "movie_ratings", "movie_names", and "actors" have a feature value for
// both movies. Note, that "actors" is itself a bytes_list with multiple
// strings per movie.
//
// context: {
// feature: {
// key : "locale"
// value: {
// bytes_list: {
// value: [ "pt_BR" ]
// }
// }
// }
// feature: {
// key : "age"
// value: {
// float_list: {
// value: [ 19.0 ]
// }
// }
// }
// feature: {
// key : "favorites"
// value: {
// bytes_list: {
// value: [ "Majesty Rose", "Savannah Outen", "One Direction" ]
// }
// }
// }
// }
// feature_lists: {
// feature_list: {
// key : "movie_ratings"
// value: {
// feature: {
// float_list: {
// value: [ 4.5 ]
// }
// }
// feature: {
// float_list: {
// value: [ 5.0 ]
// }
// }
// }
// }
// feature_list: {
// key : "movie_names"
// value: {
// feature: {
// bytes_list: {
// value: [ "The Shawshank Redemption" ]
// }
// }
// feature: {
// bytes_list: {
// value: [ "Fight Club" ]
// }
// }
// }
// }
// feature_list: {
// key : "actors"
// value: {
// feature: {
// bytes_list: {
// value: [ "Tim Robbins", "Morgan Freeman" ]
// }
// }
// feature: {
// bytes_list: {
// value: [ "Brad Pitt", "Edward Norton", "Helena Bonham Carter" ]
// }
// }
// }
// }
// }
//
// A conformant SequenceExample data set obeys the following conventions:
//
// Context:
// - All conformant context features K must obey the same conventions as
// a conformant Example's features (see above).
// Feature lists:
// - A FeatureList L may be missing in an example; it is up to the
// parser configuration to determine if this is allowed or considered
// an empty list (zero length).
// - If a FeatureList L exists, it may be empty (zero length).
// - If a FeatureList L is non-empty, all features within the FeatureList
// must have the same data type T. Even across SequenceExamples, the type T
// of the FeatureList identified by the same key must be the same. An entry
// without any values may serve as an empty feature.
// - If a FeatureList L is non-empty, it is up to the parser configuration
// to determine if all features within the FeatureList must
// have the same size. The same holds for this FeatureList across multiple
// examples.
// - For sequence modeling, e.g.:
// http://colah.github.io/posts/2015-08-Understanding-LSTMs/
// https://github.com/tensorflow/nmt
// the feature lists represent a sequence of frames.
// In this scenario, all FeatureLists in a SequenceExample have the same
// number of Feature messages, so that the ith element in each FeatureList
// is part of the ith frame (or time step).
// Examples of conformant and non-conformant examples' FeatureLists:
//
// Conformant FeatureLists:
// feature_lists: { feature_list: {
// key: "movie_ratings"
// value: { feature: { float_list: { value: [ 4.5 ] } }
// feature: { float_list: { value: [ 5.0 ] } } }
// } }
//
// Non-conformant FeatureLists (mismatched types):
// feature_lists: { feature_list: {
// key: "movie_ratings"
// value: { feature: { float_list: { value: [ 4.5 ] } }
// feature: { int64_list: { value: [ 5 ] } } }
// } }
//
// Conditionally conformant FeatureLists, the parser configuration determines
// if the feature sizes must match:
// feature_lists: { feature_list: {
// key: "movie_ratings"
// value: { feature: { float_list: { value: [ 4.5 ] } }
// feature: { float_list: { value: [ 5.0, 6.0 ] } } }
// } }
//
// Conformant pair of SequenceExample
// feature_lists: { feature_list: {
// key: "movie_ratings"
// value: { feature: { float_list: { value: [ 4.5 ] } }
// feature: { float_list: { value: [ 5.0 ] } } }
// } }
// and:
// feature_lists: { feature_list: {
// key: "movie_ratings"
// value: { feature: { float_list: { value: [ 4.5 ] } }
// feature: { float_list: { value: [ 5.0 ] } }
// feature: { float_list: { value: [ 2.0 ] } } }
// } }
//
// Conformant pair of SequenceExample
// feature_lists: { feature_list: {
// key: "movie_ratings"
// value: { feature: { float_list: { value: [ 4.5 ] } }
// feature: { float_list: { value: [ 5.0 ] } } }
// } }
// and:
// feature_lists: { feature_list: {
// key: "movie_ratings"
// value: { }
// } }
//
// Conditionally conformant pair of SequenceExample, the parser configuration
// determines if the second feature_lists is consistent (zero-length) or
// invalid (missing "movie_ratings"):
// feature_lists: { feature_list: {
// key: "movie_ratings"
// value: { feature: { float_list: { value: [ 4.5 ] } }
// feature: { float_list: { value: [ 5.0 ] } } }
// } }
// and:
// feature_lists: { }
//
// Non-conformant pair of SequenceExample (mismatched types)
// feature_lists: { feature_list: {
// key: "movie_ratings"
// value: { feature: { float_list: { value: [ 4.5 ] } }
// feature: { float_list: { value: [ 5.0 ] } } }
// } }
// and:
// feature_lists: { feature_list: {
// key: "movie_ratings"
// value: { feature: { int64_list: { value: [ 4 ] } }
// feature: { int64_list: { value: [ 5 ] } }
// feature: { int64_list: { value: [ 2 ] } } }
// } }
//
// Conditionally conformant pair of SequenceExample; the parser configuration
// determines if the feature sizes must match:
// feature_lists: { feature_list: {
// key: "movie_ratings"
// value: { feature: { float_list: { value: [ 4.5 ] } }
// feature: { float_list: { value: [ 5.0 ] } } }
// } }
// and:
// feature_lists: { feature_list: {
// key: "movie_ratings"
// value: { feature: { float_list: { value: [ 4.0 ] } }
// feature: { float_list: { value: [ 5.0, 3.0 ] } }
// } }
message SequenceExample {
Features context = 1;
FeatureLists feature_lists = 2;
};
|
