|
|
|
|
@ -18,6 +18,7 @@ package google.cloud.aiplatform.v1beta1; |
|
|
|
|
|
|
|
|
|
import "google/api/field_behavior.proto"; |
|
|
|
|
import "google/api/resource.proto"; |
|
|
|
|
import "google/cloud/aiplatform/v1beta1/encryption_spec.proto"; |
|
|
|
|
import "google/cloud/aiplatform/v1beta1/io.proto"; |
|
|
|
|
import "google/cloud/aiplatform/v1beta1/machine_resources.proto"; |
|
|
|
|
import "google/cloud/aiplatform/v1beta1/manual_batch_tuning_parameters.proto"; |
|
|
|
|
@ -79,7 +80,7 @@ message TrainingPipeline { |
|
|
|
|
// pipeline's [training_task_definition][google.cloud.aiplatform.v1beta1.TrainingPipeline.training_task_definition] contains `metadata` object. |
|
|
|
|
google.protobuf.Value training_task_metadata = 6 [(google.api.field_behavior) = OUTPUT_ONLY]; |
|
|
|
|
|
|
|
|
|
// Describes the Model that may be uploaded (via [ModelService.UploadMode][]) |
|
|
|
|
// Describes the Model that may be uploaded (via [ModelService.UploadModel][google.cloud.aiplatform.v1beta1.ModelService.UploadModel]) |
|
|
|
|
// by this TrainingPipeline. The TrainingPipeline's |
|
|
|
|
// [training_task_definition][google.cloud.aiplatform.v1beta1.TrainingPipeline.training_task_definition] should make clear whether this Model |
|
|
|
|
// description should be populated, and if there are any special requirements |
|
|
|
|
@ -125,6 +126,13 @@ message TrainingPipeline { |
|
|
|
|
// |
|
|
|
|
// See https://goo.gl/xmQnxf for more information and examples of labels. |
|
|
|
|
map<string, string> labels = 15; |
|
|
|
|
|
|
|
|
|
// Customer-managed encryption key spec for a TrainingPipeline. If set, this |
|
|
|
|
// TrainingPipeline will be secured by this key. |
|
|
|
|
// |
|
|
|
|
// Note: Model trained by this TrainingPipeline is also secured by this key if |
|
|
|
|
// [model_to_upload][google.cloud.aiplatform.v1beta1.TrainingPipeline.encryption_spec] is not set separately. |
|
|
|
|
EncryptionSpec encryption_spec = 18; |
|
|
|
|
} |
|
|
|
|
|
|
|
|
|
// Specifies AI Platform owned input data to be used for training, and |
|
|
|
|
@ -159,7 +167,7 @@ message InputDataConfig { |
|
|
|
|
// * For non-tabular data: "jsonl". |
|
|
|
|
// * For tabular data: "csv" and "bigquery". |
|
|
|
|
// |
|
|
|
|
// Following AI Platform environment variables will be passed to containers |
|
|
|
|
// The following AI Platform environment variables are passed to containers |
|
|
|
|
// or python modules of the training task when this field is set: |
|
|
|
|
// |
|
|
|
|
// * AIP_DATA_FORMAT : Exported data format. |
|
|
|
|
@ -167,43 +175,50 @@ message InputDataConfig { |
|
|
|
|
// * AIP_VALIDATION_DATA_URI : Sharded exported validation data uris. |
|
|
|
|
// * AIP_TEST_DATA_URI : Sharded exported test data uris. |
|
|
|
|
oneof destination { |
|
|
|
|
// The Google Cloud Storage location where the training data is to be |
|
|
|
|
// written to. In the given directory a new directory will be created with |
|
|
|
|
// The Cloud Storage location where the training data is to be |
|
|
|
|
// written to. In the given directory a new directory is created with |
|
|
|
|
// name: |
|
|
|
|
// `dataset-<dataset-id>-<annotation-type>-<timestamp-of-training-call>` |
|
|
|
|
// where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format. |
|
|
|
|
// All training input data will be written into that directory. |
|
|
|
|
// All training input data is written into that directory. |
|
|
|
|
// |
|
|
|
|
// The AI Platform environment variables representing Google Cloud Storage |
|
|
|
|
// data URIs will always be represented in the Google Cloud Storage wildcard |
|
|
|
|
// The AI Platform environment variables representing Cloud Storage |
|
|
|
|
// data URIs are represented in the Cloud Storage wildcard |
|
|
|
|
// format to support sharded data. e.g.: "gs://.../training-*.jsonl" |
|
|
|
|
// |
|
|
|
|
// * AIP_DATA_FORMAT = "jsonl" for non-tabular data, "csv" for tabular data |
|
|
|
|
// * AIP_TRAINING_DATA_URI = |
|
|
|
|
// * AIP_TRAINING_DATA_URI = |
|
|
|
|
// |
|
|
|
|
// "gcs_destination/dataset-<dataset-id>-<annotation-type>-<time>/training-*.${AIP_DATA_FORMAT}" |
|
|
|
|
// |
|
|
|
|
// * AIP_VALIDATION_DATA_URI = |
|
|
|
|
// |
|
|
|
|
// "gcs_destination/dataset-<dataset-id>-<annotation-type>-<time>/validation-*.${AIP_DATA_FORMAT}" |
|
|
|
|
// |
|
|
|
|
// * AIP_TEST_DATA_URI = |
|
|
|
|
// |
|
|
|
|
// "gcs_destination/dataset-<dataset-id>-<annotation-type>-<time>/test-*.${AIP_DATA_FORMAT}" |
|
|
|
|
GcsDestination gcs_destination = 8; |
|
|
|
|
|
|
|
|
|
// Only applicable to custom training with tabular Dataset with BigQuery |
|
|
|
|
// source. |
|
|
|
|
// |
|
|
|
|
// The BigQuery project location where the training data is to be written |
|
|
|
|
// to. In the given project a new dataset is created with name |
|
|
|
|
// `dataset_<dataset-id>_<annotation-type>_<timestamp-of-training-call>` |
|
|
|
|
// where timestamp is in YYYY_MM_DDThh_mm_ss_sssZ format. All training |
|
|
|
|
// input data will be written into that dataset. In the dataset three |
|
|
|
|
// tables will be created, `training`, `validation` and `test`. |
|
|
|
|
// input data is written into that dataset. In the dataset three |
|
|
|
|
// tables are created, `training`, `validation` and `test`. |
|
|
|
|
// |
|
|
|
|
// * AIP_DATA_FORMAT = "bigquery". |
|
|
|
|
// * AIP_TRAINING_DATA_URI = |
|
|
|
|
// |
|
|
|
|
// "bigquery_destination.dataset_<dataset-id>_<annotation-type>_<time>.training" |
|
|
|
|
// |
|
|
|
|
// * AIP_VALIDATION_DATA_URI = |
|
|
|
|
// |
|
|
|
|
// "bigquery_destination.dataset_<dataset-id>_<annotation-type>_<time>.validation" |
|
|
|
|
// |
|
|
|
|
// * AIP_TEST_DATA_URI = |
|
|
|
|
// "bigquery_destination.dataset_<dataset-id>_<annotation-type>_<time>.test" |
|
|
|
|
BigQueryDestination bigquery_destination = 10; |
|
|
|
|
@ -218,7 +233,7 @@ message InputDataConfig { |
|
|
|
|
// and choose from. |
|
|
|
|
string dataset_id = 1 [(google.api.field_behavior) = REQUIRED]; |
|
|
|
|
|
|
|
|
|
// Only applicable to Datasets that have DataItems and Annotations. |
|
|
|
|
// Applicable only to Datasets that have DataItems and Annotations. |
|
|
|
|
// |
|
|
|
|
// A filter on Annotations of the Dataset. Only Annotations that both |
|
|
|
|
// match this filter and belong to DataItems not ignored by the split method |
|
|
|
|
@ -230,16 +245,14 @@ message InputDataConfig { |
|
|
|
|
// a single DataItem. |
|
|
|
|
string annotations_filter = 6; |
|
|
|
|
|
|
|
|
|
// Only applicable to custom training. |
|
|
|
|
// |
|
|
|
|
// Google Cloud Storage URI points to a YAML file describing annotation |
|
|
|
|
// schema. The schema is defined as an OpenAPI 3.0.2 [Schema Object]( |
|
|
|
|
// Applicable only to custom training with Datasets that have DataItems and |
|
|
|
|
// Annotations. |
|
|
|
|
// |
|
|
|
|
// https: |
|
|
|
|
// //github.com/OAI/OpenAPI-Specification/b |
|
|
|
|
// // lob/master/versions/3.0.2.md#schema-object) |
|
|
|
|
// Cloud Storage URI that points to a YAML file describing the annotation |
|
|
|
|
// schema. The schema is defined as an OpenAPI 3.0.2 |
|
|
|
|
// [Schema Object](https://tinyurl.com/y538mdwt#schema-object). |
|
|
|
|
// The schema files that can be used here are found in |
|
|
|
|
// gs://google-cloud-aiplatform/schema/dataset/annotation/, note that the |
|
|
|
|
// gs://google-cloud-aiplatform/schema/dataset/annotation/ , note that the |
|
|
|
|
// chosen schema must be consistent with |
|
|
|
|
// [metadata][google.cloud.aiplatform.v1beta1.Dataset.metadata_schema_uri] of the Dataset specified by |
|
|
|
|
// [dataset_id][google.cloud.aiplatform.v1beta1.InputDataConfig.dataset_id]. |
|
|
|
|
@ -259,7 +272,7 @@ message InputDataConfig { |
|
|
|
|
// `test_fraction` may optionally be provided, they must sum to up to 1. If the |
|
|
|
|
// provided ones sum to less than 1, the remainder is assigned to sets as |
|
|
|
|
// decided by AI Platform. If none of the fractions are set, by default roughly |
|
|
|
|
// 80% of data will be used for training, 10% for validation, and 10% for test. |
|
|
|
|
// 80% of data is used for training, 10% for validation, and 10% for test. |
|
|
|
|
message FractionSplit { |
|
|
|
|
// The fraction of the input data that is to be used to train the Model. |
|
|
|
|
double training_fraction = 1; |
|
|
|
|
@ -276,12 +289,15 @@ message FractionSplit { |
|
|
|
|
// supported for Datasets containing DataItems. |
|
|
|
|
// If any of the filters in this message are to match nothing, then they can be |
|
|
|
|
// set as '-' (the minus sign). |
|
|
|
|
// |
|
|
|
|
// Supported only for unstructured Datasets. |
|
|
|
|
// |
|
|
|
|
message FilterSplit { |
|
|
|
|
// Required. A filter on DataItems of the Dataset. DataItems that match |
|
|
|
|
// this filter are used to train the Model. A filter with same syntax |
|
|
|
|
// as the one used in [DatasetService.ListDataItems][google.cloud.aiplatform.v1beta1.DatasetService.ListDataItems] may be used. If a |
|
|
|
|
// single DataItem is matched by more than one of the FilterSplit filters, |
|
|
|
|
// then it will be assigned to the first set that applies to it in the |
|
|
|
|
// then it is assigned to the first set that applies to it in the |
|
|
|
|
// training, validation, test order. |
|
|
|
|
string training_filter = 1 [(google.api.field_behavior) = REQUIRED]; |
|
|
|
|
|
|
|
|
|
@ -289,7 +305,7 @@ message FilterSplit { |
|
|
|
|
// this filter are used to validate the Model. A filter with same syntax |
|
|
|
|
// as the one used in [DatasetService.ListDataItems][google.cloud.aiplatform.v1beta1.DatasetService.ListDataItems] may be used. If a |
|
|
|
|
// single DataItem is matched by more than one of the FilterSplit filters, |
|
|
|
|
// then it will be assigned to the first set that applies to it in the |
|
|
|
|
// then it is assigned to the first set that applies to it in the |
|
|
|
|
// training, validation, test order. |
|
|
|
|
string validation_filter = 2 [(google.api.field_behavior) = REQUIRED]; |
|
|
|
|
|
|
|
|
|
@ -297,7 +313,7 @@ message FilterSplit { |
|
|
|
|
// this filter are used to test the Model. A filter with same syntax |
|
|
|
|
// as the one used in [DatasetService.ListDataItems][google.cloud.aiplatform.v1beta1.DatasetService.ListDataItems] may be used. If a |
|
|
|
|
// single DataItem is matched by more than one of the FilterSplit filters, |
|
|
|
|
// then it will be assigned to the first set that applies to it in the |
|
|
|
|
// then it is assigned to the first set that applies to it in the |
|
|
|
|
// training, validation, test order. |
|
|
|
|
string test_filter = 3 [(google.api.field_behavior) = REQUIRED]; |
|
|
|
|
} |
|
|
|
|
|
Google APIs
4 years ago
committed by
Copybara-Service