Index
AutoMl
(interface)PredictionService
(interface)AnnotationPayload
(message)AnnotationSpec
(message)BatchPredictInputConfig
(message)BatchPredictOperationMetadata
(message)BatchPredictOperationMetadata.BatchPredictOutputInfo
(message)BatchPredictOutputConfig
(message)BatchPredictRequest
(message)BatchPredictResult
(message)BigQueryDestination
(message)ClassificationAnnotation
(message)ClassificationEvaluationMetrics
(message)ClassificationEvaluationMetrics.ConfidenceMetricsEntry
(message)ClassificationEvaluationMetrics.ConfusionMatrix
(message)ClassificationEvaluationMetrics.ConfusionMatrix.Row
(message)CreateDatasetRequest
(message)CreateModelOperationMetadata
(message)CreateModelRequest
(message)Dataset
(message)DeleteDatasetRequest
(message)DeleteModelRequest
(message)DeleteOperationMetadata
(message)DeployModelOperationMetadata
(message)DeployModelRequest
(message)ExamplePayload
(message)ExportDataOperationMetadata
(message)ExportDataOperationMetadata.ExportDataOutputInfo
(message)ExportDataRequest
(message)GcsDestination
(message)GcsSource
(message)GetAnnotationSpecRequest
(message)GetDatasetRequest
(message)GetModelEvaluationRequest
(message)GetModelRequest
(message)ImportDataOperationMetadata
(message)ImportDataRequest
(message)InputConfig
(message)ListDatasetsRequest
(message)ListDatasetsResponse
(message)ListModelEvaluationsRequest
(message)ListModelEvaluationsResponse
(message)ListModelsRequest
(message)ListModelsResponse
(message)Model
(message)Model.DeploymentState
(enum)ModelEvaluation
(message)OperationMetadata
(message)OutputConfig
(message)PredictRequest
(message)PredictResponse
(message)TimeSegment
(message)UndeployModelOperationMetadata
(message)UndeployModelRequest
(message)VideoClassificationAnnotation
(message)VideoClassificationDatasetMetadata
(message)VideoClassificationModelMetadata
(message)
AutoMl
AutoML Server API.
The resource names are assigned by the server. The server never reuses names that it has created after the resources with those names are deleted.
An ID of a resource is the last element of the item's resource name. For projects/{project_id}/locations/{location_id}/datasets/{dataset_id}
, then the id for the item is {dataset_id}
.
Currently the only supported location_id
is "us-central1".
On any input that is documented to expect a string parameter in snake_case or dash-case, either of those cases is accepted.
CreateDataset | |
---|---|
Creates a dataset.
|
CreateModel | |
---|---|
Creates a model. Returns a Model in the
|
DeleteDataset | |
---|---|
Deletes a dataset and all of its contents. Returns empty response in the
|
DeleteModel | |
---|---|
Deletes a model. Returns
|
DeployModel | |
---|---|
Deploys a model. Not applicable for this product. This product automatically deploys models when they are successfully trained. Returns an empty response in the
|
ExportData | |
---|---|
Exports dataset's data to the provided output location. Returns an empty response in the
|
GetAnnotationSpec | |
---|---|
Gets an annotation spec.
|
GetDataset | |
---|---|
Gets a dataset.
|
GetModel | |
---|---|
Gets a model.
|
GetModelEvaluation | |
---|---|
Gets a model evaluation.
|
ImportData | |
---|---|
Imports data into a dataset. You can only call this method for an empty Dataset. For more information, see Importing items into a dataset
|
ListDatasets | |
---|---|
Lists datasets in a project.
|
ListModelEvaluations | |
---|---|
Lists model evaluations.
|
ListModels | |
---|---|
Lists models.
|
UndeployModel | |
---|---|
Removes a deployed model. Not applicable for this product. This product automatically removes deployed models that are deleted. Returns an empty response in the
|
PredictionService
AutoML Prediction API.
On any input that is documented to expect a string parameter in snake_case or dash-case, either of those cases is accepted.
BatchPredict | |
---|---|
Perform a batch prediction and return the id of a long-running operation. You can request the operation result by using the
|
Predict | |
---|---|
Not available for AutoML Video Intelligence.
|
AnnotationPayload
Contains annotation information that is relevant to AutoML.
Fields | ||
---|---|---|
annotation_spec_id |
Output only . The resource ID of the annotation spec that this annotation pertains to. The annotation spec comes from either an ancestor dataset, or the dataset that was used to train the model in use. |
|
display_name |
Output only. The value of |
|
Union field detail . Output only . Additional information about the annotation specific to the AutoML domain. detail can be only one of the following: |
||
classification |
Annotation details for classification predictions. |
|
video_classification |
Annotation details for video classification. Returned for Video Classification predictions. |
AnnotationSpec
A definition of an annotation.
Fields | |
---|---|
name |
Output only. Resource name of the annotation spec. Form: 'projects/{project_id}/locations/{location_id}/datasets/{dataset_id}/annotationSpecs/{annotation_spec_id}' |
display_name |
Required. The name of the annotation spec to show in the interface. The name can be up to 32 characters long and can consist only of ASCII Latin letters A-Z and a-z, underscores (_), and ASCII digits 0-9. |
example_count |
Output only. The number of examples in the parent dataset labeled by the annotation spec. |
BatchPredictInputConfig
Input configuration for BatchPredict
action. The input is one or more CSV files stored in Google Cloud Storage where the CSV files are in the following format:
GCS_FILE_PATH,TIME_SEGMENT_START,TIME_SEGMENT_END
GCS_FILE_PATH
identifies the Google Cloud Storage path to a video up to 50GB in size and up to 3h duration. Supported extensions: .MOV, .MPEG4, .MP4, .AVI.TIME_SEGMENT_START
andTIME_SEGMENT_END
must be within the length of the video, and end has to be after the start.
Three sample rows:
gs://folder/video1.mp4,10,40
gs://folder/video1.mp4,20,60
gs://folder/vid2.mov,0,inf
See Annotating videos for more information.
Fields | |
---|---|
gcs_source |
The Google Cloud Storage location for the input content. |
BatchPredictOperationMetadata
Details of BatchPredict operation.
Fields | |
---|---|
input_config |
Output only. The input config that was given upon starting this batch predict operation. |
output_info |
Output only. Information further describing this batch predict's output. |
BatchPredictOutputInfo
Further describes this batch predict's output. Supplements
Fields | ||
---|---|---|
Union field output_location . The output location into which prediction output is written. output_location can be only one of the following: |
||
gcs_output_directory |
The full path of the Google Cloud Storage directory created, into which the prediction output is written. |
|
bigquery_output_dataset |
The path of the BigQuery dataset created, in bq://projectId.bqDatasetId format, into which the prediction output is written. |
BatchPredictOutputConfig
Output configuration for BatchPredict
Action.
AutoML Video Intelligence creates a directory specified in the
. The name of the directory is "prediction-<model-display-name>-<timestamp-of-prediction-call>", where timestamp is in gcsDestination
YYYY-MM-DDThh:mm:ss.sssZ
ISO-8601 format.
AutoML Video Intelligence creates a file named video_classification.csv in the new directory, and also a JSON file for each video classification requested. That is, each row in the input CSV file.
The format of the video_classification.csv file is as follows:
GCS_FILE_PATH,TIME_SEGMENT_START,TIME_SEGMENT_END,JSON_FILE_NAME,STATUS
The
GCS_FILE_PATH
,TIME_SEGMENT_START
,TIME_SEGMENT_END
match the same fields from the input CSV file.JSON_FILE_NAME
is the name of the JSON file in the output directory that contains prediction responses for the video time segment.STATUS
contains "OK" if the prediction completed successfully; otherwise contains error information. IfSTATUS
is not "OK" then the JSON file for that prediction might be empty or the file might not exist.
Each JSON file where STATUS
is "OK", contains a list of AnnotationPayload protos in JSON format, which are the predictions for the video time segment the file is assigned to in the video_classification.csv. All AnnotationPayload protos have a video_classification
field, and are sorted by the video_classification.type
field. The types returned are determined by the classifaction_types
parameter of BatchPredictRequest.params
.
Fields | ||
---|---|---|
Union field destination . Required. The destination of the output. destination can be only one of the following: |
||
gcs_destination |
The Google Cloud Storage location of the directory where the output is to be written to. |
|
bigquery_destination |
The BigQuery location where the output is to be written to. |
BatchPredictRequest
Request message for PredictionService.BatchPredict
.
Fields | |||||||||
---|---|---|---|---|---|---|---|---|---|
name |
Name of the model requested to serve the batch prediction. Authorization requires the following Google IAM permission on the specified resource
|
||||||||
input_config |
Required. The input configuration for batch prediction. |
||||||||
output_config |
Required. The Configuration specifying where output predictions should be written. |
||||||||
params |
Can be one of the following:
See Annotating videos for more details. |
BatchPredictResult
Result of the Batch Predict. This message is returned in response
of the operation returned by the PredictionService.BatchPredict
.
Fields | |
---|---|
metadata |
Additional domain-specific prediction response metadata. |
BigQueryDestination
The BigQuery location for the output content.
Fields | |
---|---|
output_uri |
Required. BigQuery URI to a project, up to 2000 characters long. For example: |
ClassificationAnnotation
Contains annotation details specific to classification.
Fields | |
---|---|
score |
Output only. A confidence estimate between 0.0 and 1.0. A higher value means greater confidence that the annotation is positive. If a user approves an annotation as negative or positive, the score value remains unchanged. If a user creates an annotation, the score is 0 for negative or 1 for positive. |
ClassificationEvaluationMetrics
Model evaluation metrics for classification problems. These metrics only describe the quality of predictions where the type is set to segment_classification
. For information on the prediction type, see BatchPredictRequest.params
.
Fields | |
---|---|
au_prc |
Output only. The Area Under Precision-Recall Curve metric. Micro-averaged for the overall evaluation. |
base_au_prc |
Output only. The Area Under Precision-Recall Curve metric based on priors. Micro-averaged for the overall evaluation. Deprecated. |
au_roc |
Output only. The Area Under Receiver Operating Characteristic curve metric. Micro-averaged for the overall evaluation. |
log_loss |
Output only. The Log Loss metric. |
confidence_metrics_entry[] |
Output only. Metrics for each confidence_threshold in 0.00,0.05,0.10,...,0.95,0.96,0.97,0.98,0.99 and position_threshold = INT32_MAX_VALUE. ROC and precision-recall curves, and other aggregated metrics are derived from them. The confidence metrics entries may also be supplied for additional values of position_threshold, but from these no aggregated metrics are computed. |
confusion_matrix |
Output only. Confusion matrix of the evaluation. Only set for MULTICLASS classification problems where number of labels is no more than 10. Only set for model level evaluation, not for evaluation per label. |
annotation_spec_id[] |
Output only. The annotation spec ids used for this evaluation. |
ConfidenceMetricsEntry
Metrics for a single confidence threshold.
Fields | |
---|---|
confidence_threshold |
Output only. Metrics are computed with an assumption that the model never returns predictions with score lower than this value. |
position_threshold |
Output only. Metrics are computed with an assumption that the model always returns at most this many predictions (ordered by their score, descendingly), but they all still need to meet the confidence_threshold. |
recall |
Output only. Recall (True Positive Rate) for the given confidence threshold. |
precision |
Output only. Precision for the given confidence threshold. |
false_positive_rate |
Output only. False Positive Rate for the given confidence threshold. |
f1_score |
Output only. The harmonic mean of recall and precision. |
recall_at1 |
Output only. The Recall (True Positive Rate) when only considering the label that has the highest prediction score and not below the confidence threshold for each example. |
precision_at1 |
Output only. The precision when only considering the label that has the highest prediction score and not below the confidence threshold for each example. |
false_positive_rate_at1 |
Output only. The False Positive Rate when only considering the label that has the highest prediction score and not below the confidence threshold for each example. |
f1_score_at1 |
Output only. The harmonic mean of |
true_positive_count |
Output only. The number of model created labels that match a ground truth label. |
false_positive_count |
Output only. The number of model created labels that do not match a ground truth label. |
false_negative_count |
Output only. The number of ground truth labels that are not matched by a model created label. |
true_negative_count |
Output only. The number of labels that were not created by the model, but if they would, they would not match a ground truth label. |
ConfusionMatrix
Confusion matrix of the model running the classification.
Fields | |
---|---|
annotation_spec_id[] |
Output only. IDs of the annotation specs used in the confusion matrix. |
row[] |
Output only. Rows in the confusion matrix. The number of rows is equal to the size of |
Row
Output only. A row in the confusion matrix.
Fields | |
---|---|
example_count[] |
Output only. Value of the specific cell in the confusion matrix. The number of values each row has (i.e. the length of the row) is equal to the length of the |
CreateDatasetRequest
Request message for AutoMl.CreateDataset
.
Fields | |
---|---|
parent |
The resource name of the project to create the dataset for. Authorization requires the following Google IAM permission on the specified resource
|
dataset |
The dataset to create. |
CreateModelOperationMetadata
Details of CreateModel operation.
CreateModelRequest
Request message for AutoMl.CreateModel
.
Fields | |
---|---|
parent |
Resource name of the parent project where the model is being created. Authorization requires the following Google IAM permission on the specified resource
|
model |
The model to create. |
Dataset
A workspace for solving a single, particular machine learning (ML) problem. A workspace contains examples that may be annotated.
Fields | |
---|---|
name |
Output only. The resource name of the dataset. Form: |
display_name |
Required. The name of the dataset to show in the interface. The name can be up to 32 characters long and can consist only of ASCII Latin letters A-Z and a-z, underscores (_), and ASCII digits 0-9. |
example_count |
Output only. The number of examples in the dataset. |
create_time |
Output only. Timestamp when this dataset was created. |
video_classification_dataset_metadata |
Metadata for a dataset used for video classification. |
DeleteDatasetRequest
Request message for AutoMl.DeleteDataset
.
Fields | |
---|---|
name |
The resource name of the dataset to delete. Authorization requires the following Google IAM permission on the specified resource
|
DeleteModelRequest
Request message for AutoMl.DeleteModel
.
Fields | |
---|---|
name |
Resource name of the model being deleted. Authorization requires the following Google IAM permission on the specified resource
|
DeleteOperationMetadata
Details of operations that perform deletes of any entities.
DeployModelOperationMetadata
Details of DeployModel operation.
DeployModelRequest
Request message for AutoMl.DeployModel
.
Fields | |
---|---|
name |
Resource name of the model to deploy. Authorization requires the following Google IAM permission on the specified resource
|
ExamplePayload
Example data used for training or prediction.
ExportDataOperationMetadata
Details of ExportData operation.
Fields | |
---|---|
output_info |
Output only. Information further describing this export data's output. |
ExportDataOutputInfo
Further describes this export data's output. Supplements OutputConfig
.
Fields | ||
---|---|---|
Union field output_location . The output location to which the exported data is written. output_location can be only one of the following: |
||
gcs_output_directory |
The full path of the Google Cloud Storage directory created, into which the exported data is written. |
|
bigquery_output_dataset |
The path of the BigQuery dataset created, in bq://projectId.bqDatasetId format, into which the exported data is written. |
ExportDataRequest
Request message for AutoMl.ExportData
.
Fields | |
---|---|
name |
Required. The resource name of the dataset. Authorization requires the following Google IAM permission on the specified resource
|
output_config |
Required. The desired output location. |
GcsDestination
The Google Cloud Storage location where the output is to be written to.
Fields | |
---|---|
output_uri_prefix |
Required. Google Cloud Storage URI to output directory, up to 2000 characters long. Accepted forms: * Prefix path: gs://bucket/directory The requesting user must have write permission to the bucket. The directory is created if it doesn't exist. |
GcsSource
The Google Cloud Storage location for the input content.
Fields | |
---|---|
input_uris[] |
Required. Google Cloud Storage URIs to input files, up to 2000 characters long. Accepted forms: * Full object path, e.g. gs://bucket/directory/object.csv |
GetAnnotationSpecRequest
Request message for AutoMl.GetAnnotationSpec
.
Fields | |
---|---|
name |
The resource name of the annotation spec to retrieve. Authorization requires the following Google IAM permission on the specified resource
|
GetDatasetRequest
Request message for AutoMl.GetDataset
.
Fields | |
---|---|
name |
The resource name of the dataset to retrieve. Authorization requires the following Google IAM permission on the specified resource
|
GetModelEvaluationRequest
Request message for AutoMl.GetModelEvaluation
.
Fields | |
---|---|
name |
Resource name for the model evaluation. Authorization requires the following Google IAM permission on the specified resource
|
GetModelRequest
Request message for AutoMl.GetModel
.
Fields | |
---|---|
name |
Resource name of the model. Authorization requires the following Google IAM permission on the specified resource
|
ImportDataOperationMetadata
Details of ImportData operation.
ImportDataRequest
Request message for AutoMl.ImportData
.
Fields | |
---|---|
name |
Required. Dataset name. Dataset must already exist. All imported annotations and examples will be added. Authorization requires the following Google IAM permission on the specified resource
|
input_config |
Required. The desired input location and its domain specific semantics, if any. |
InputConfig
Input configuration for ImportData
action.
The format of input depends on dataset_metadata the Dataset into which the import is happening has. As input source the gcs_source
is expected, unless specified otherwise. If a file with identical content (even if it had different GCS_FILE_PATH
) is mentioned multiple times , then its label, bounding boxes etc. are appended. The same file should be always provided with the same ML_USE
and GCS_FILE_PATH
, if it is not then these values are nondeterministically selected from the given ones.
The formats are represented in EBNF with commas being literal and with non-terminal symbols defined near the end of this comment. The formats are:
See Preparing your training data for more information.
A CSV file(s) with each line in format:
ML_USE,GCS_FILE_PATH
ML_USE
- Identifies the data set that the current row (file) applies to. This value can be one of the following:TRAIN
- Rows in this file are used to train the model.TEST
- Rows in this file are used to test the model during training.UNASSIGNED
- Rows in this file are not categorized. They are Automatically divided into train and test data. 80% for training and 20% for testing.
GCS_FILE_PATH
- Identifies a file stored in Google Cloud Storage that contains the model training information.
After the training data set has been determined from the TRAIN
and UNASSIGNED
CSV files, the training data is divided into train and validation data sets. 70% for training and 30% for validation.
Each CSV file specified using the GCS_FILE_PATH
field has the following format:
GCS_FILE_PATH,LABEL,TIME_SEGMENT_START,TIME_SEGMENT_END
GCS_FILE_PATH
- The path to a video stored in Google Cloud Storage. The video can be up to 1h duration. Supported extensions: .MOV, .MPEG4, .MP4, .AVI.LABEL
- A label that identifies the object of the video segment.TIME_SEGMENT_START
andTIME_SEGMENT_END
- The start and end timestamps in seconds for the segment of video to be annotated. The values must be within the length of the video, andTIME_SEGMENT_END
must be after theTIME_SEGMENT_START
.
You can specify videos in the CSV file without any labels. You must then use the AutoML Video Intelligence UI to apply labels to the video before you train your model. To specify a video segment in this way, provide the Google Cloud Storage URI for the video followed by three commas.
Sample file:
TRAIN,gs:folder/train_videos.csv
TEST,gs:folder/test_videos.csv
UNASSIGNED,gs:folder/other_videos.csv
Here is an example of the format of one of the CSV files identified by the gcsSource
"top level" file.
gs://folder/video1.avi,car,120,180.000021
gs://folder/video1.avi,bike,150,180.000021
gs://folder/vid2.avi,car,0,60.5
gs://folder/vid3.avi,,,
Errors:
If any of the provided CSV files can't be parsed or if more than certain percent of CSV rows cannot be processed then the operation fails and nothing is imported. Regardless of overall success or failure the per-row failures, up to a certain count cap, will be listed in Operation.metadata.partial_failures.
Fields | |
---|---|
gcs_source |
The Google Cloud Storage location for the input content. |
ListDatasetsRequest
Request message for AutoMl.ListDatasets
.
Fields | |
---|---|
parent |
The resource name of the project from which to list datasets. Authorization requires the following Google IAM permission on the specified resource
|
filter |
An expression for filtering the results of the request.
An example of using the filter is:
|
page_size |
Requested page size. Server may return fewer results than requested. If unspecified, server will pick a default size. |
page_token |
A token identifying a page of results for the server to return Typically obtained via |
ListDatasetsResponse
Response message for AutoMl.ListDatasets
.
Fields | |
---|---|
datasets[] |
The datasets read. |
next_page_token |
A token to retrieve next page of results. Pass to |
ListModelEvaluationsRequest
Request message for AutoMl.ListModelEvaluations
.
Fields | |
---|---|
parent |
Resource name of the model to list the model evaluations for. If modelId is set as "-", this will list model evaluations from across all models of the parent location. Authorization requires the following Google IAM permission on the specified resource
|
filter |
An expression for filtering the results of the request.
Some examples of using the filter are:
|
page_size |
Requested page size. |
page_token |
A token identifying a page of results for the server to return. Typically obtained via |
ListModelEvaluationsResponse
Response message for AutoMl.ListModelEvaluations
.
Fields | |
---|---|
model_evaluation[] |
List of model evaluations in the requested page. |
next_page_token |
A token to retrieve next page of results. Pass to the |
ListModelsRequest
Request message for AutoMl.ListModels
.
Fields | |
---|---|
parent |
Resource name of the project, from which to list the models. Authorization requires the following Google IAM permission on the specified resource
|
filter |
An expression for filtering the results of the request.
Some examples of using the filter are:
|
page_size |
Requested page size. |
page_token |
A token identifying a page of results for the server to return Typically obtained via |
ListModelsResponse
Response message for AutoMl.ListModels
.
Fields | |
---|---|
model[] |
List of models in the requested page. |
next_page_token |
A token to retrieve next page of results. Pass to |
Model
API proto representing a trained machine learning model.
Fields | |
---|---|
name |
Output only. Resource name of the model. Format: |
display_name |
Required. The name of the model to show in the interface. The name can be up to 32 characters long and can consist only of ASCII Latin letters A-Z and a-z, underscores (_), and ASCII digits 0-9. It must start with a letter. |
dataset_id |
Required. The resource ID of the dataset used to create the model. The dataset must come from the same ancestor project and location. |
create_time |
Output only. Timestamp when the model training finished and can be used for prediction. |
update_time |
Output only. Timestamp when this model was last updated. |
deployment_state |
Output only. Deployment state of the model. A model can only serve prediction requests after it gets deployed. |
video_classification_model_metadata |
Metadata for video classification models. |
DeploymentState
Deployment state of the model.
Enums | |
---|---|
DEPLOYMENT_STATE_UNSPECIFIED |
Should not be used, an un-set enum has this value by default. |
DEPLOYED |
Model is deployed. |
UNDEPLOYED |
Model is not deployed. |
ModelEvaluation
Evaluation results of a model.
Fields | |
---|---|
name |
Output only. Resource name of the model evaluation. Format:
|
annotation_spec_id |
Output only. The ID of the annotation spec that the model evaluation applies to. The The ID is empty for the overall model evaluation. |
display_name |
Output only. The value of The display_name is empty for the overall model evaluation. |
create_time |
Output only. Timestamp when this model evaluation was created. |
evaluated_example_count |
Output only. The number of examples used for model evaluation, i.e. for which ground truth from time of model creation is compared against the predicted annotations created by the model. For overall ModelEvaluation (i.e. with annotation_spec_id not set) this is the total number of all examples used for evaluation. Otherwise, this is the count of examples that according to the ground truth were annotated by the |
classification_evaluation_metrics |
Evaluation metrics for classification models. |
OperationMetadata
Metadata used across all long running operations returned by AutoML API.
Fields | ||
---|---|---|
progress_percent |
Output only. Progress of operation. Range: [0, 100]. Not used currently. |
|
partial_failures[] |
Output only. Partial failures encountered. E.g. single files that couldn't be read. This field should never exceed 20 entries. Status details field will contain standard GCP error details. |
|
create_time |
Output only. Time when the operation was created. |
|
update_time |
Output only. Time when the operation was updated for the last time. |
|
Union field details . Ouptut only. Details of specific operation. Even if this field is empty, the presence allows to distinguish different types of operations. details can be only one of the following: |
||
delete_details |
Details of a Delete operation. |
|
deploy_model_details |
Details of a DeployModel operation. |
|
undeploy_model_details |
Details of an UndeployModel operation. |
|
create_model_details |
Details of CreateModel operation. |
|
import_data_details |
Details of ImportData operation. |
|
batch_predict_details |
Details of BatchPredict operation. |
|
export_data_details |
Details of ExportData operation. |
OutputConfig
Output configuration for ExportData
.
AutoML Video Intelligence writes a CSV file named video_classification.csv
in the Google Cloud Storage bucket specified in gcs_destination
.
The output file has the following fields:
ML_USE,GCS_FILE_PATH
ML_USE
- Identifies the data set that the current row (file) applies to. This value can be one of the following:TRAIN
- Rows in this file are used to train the model.TEST
- Rows in this file are used to test the model during training.UNASSIGNED
- Rows in this file are not categorized. They are Automatically divided into train and test data. 80% for training and 20% for testing.
GCS_FILE_PATH
- Identifies a file stored in Google Cloud Storage that contains the model training information. AutoML Video Intelligence writes this file to the Google Cloud Storage bucket specified ingcs_destination
.
Each CSV file identified with a GCS_FILE_PATH
value has the following format:
GCS_FILE_PATH,LABEL,TIME_SEGMENT_START,TIME_SEGMENT_END
GCS_FILE_PATH
- The path to the original, imported video stored in Google Cloud Storage.LABEL
- The label that identifies the object of the imported video segment.TIME_SEGMENT_START
andTIME_SEGMENT_END
- The start and end timestamps in seconds for the segment of video to be annotated. The values must be within the length of the video, andTIME_SEGMENT_END
must be after theTIME_SEGMENT_START
.
Fields | |
---|---|
gcs_destination |
The Google Cloud Storage location where the output from the |
PredictRequest
Request message for PredictionService.Predict
.
Fields | |
---|---|
name |
Name of the model requested to serve the prediction. Authorization requires the following Google IAM permission on the specified resource
|
payload |
Required. Payload to perform a prediction on. The payload must match the problem type that the model was trained to solve. |
params |
Additional domain-specific parameters, any string must be up to 25000 characters long. |
PredictResponse
Response message for PredictionService.Predict
.
Fields | |
---|---|
payload[] |
Prediction result. |
metadata |
Additional domain-specific prediction response metadata. |
TimeSegment
A time period inside of an example that has a time dimension (e.g. video).
Fields | |
---|---|
start_time_offset |
Start of the time segment (inclusive), represented as the duration since the example start. |
end_time_offset |
End of the time segment (exclusive), represented as the duration since the example start. |
UndeployModelOperationMetadata
Details of UndeployModel operation.
UndeployModelRequest
Request message for AutoMl.UndeployModel
.
Fields | |
---|---|
name |
Resource name of the model to undeploy. Authorization requires the following Google IAM permission on the specified resource
|
VideoClassificationAnnotation
Contains annotation details specific to video classification.
Fields | |
---|---|
type |
Output only. Expresses the type of video classification. Possible values:
|
classification_annotation |
Output only . The classification details of this annotation. |
time_segment |
Output only . The time segment of the video to which the annotation applies. |
VideoClassificationDatasetMetadata
Dataset metadata specific to video classification. All Video Classification datasets are treated as multi label.
VideoClassificationModelMetadata
Model metadata specific to video classification.