TensorFlow用于描述输入数据的协议消息的机器学习示例
2018-09-27 17:23 更新
//用于描述输入数据的协议消息机器学习示例
//模型训练或推理.
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";
package tensorflow;
//一个例子是用于存储数据的大多数归一化的数据格式
//训练和推理.它包含一个键值存储(特征);
//每个键(字符串)映射到一个Feature消息(这是一个打包BytesList,
// FloatList或Int64List).这种灵活和紧凑的格式允许
//存储大量的类型数据,但要求数据形状
//并使用由用于的配置文件和解析器确定
//读取和写入此格式.也就是说,这个例子主要不是
//自描述格式.在TensorFlow中,示例是以行为主的读取
//格式,所以任何描述具有2级或更高级别的数据的配置
//应该记住这一点.例如,为了存储一个M×N字节的矩阵,
// BytesList 必须包含M * N个字节,M行N个连续值,
//每个,也就是说,BytesList 值必须将矩阵存储为：
// .... row 0 .... .... row 1 .... // ........... // ... row M-1 ....
//
//电影推荐应用程序的示例：
// 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.
//
// 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;
};