com.amazonaws.services.sagemaker.model

Class InputConfig

java.lang.Object

com.amazonaws.services.sagemaker.model.InputConfig

All Implemented Interfaces:

StructuredPojo, Serializable, Cloneable

@Generated(value="com.amazonaws:aws-java-sdk-code-generator")
public class InputConfig
extends Object
implements Serializable, Cloneable, StructuredPojo

Contains information about the location of input model artifacts, the name and shape of the expected data inputs, and the framework in which the model was trained.

See Also:

AWS API Documentation, Serialized Form

Constructor Summary

Constructors

Constructor and Description
InputConfig()

Method Summary

Modifier and Type	Method and Description
InputConfig	clone()
boolean	equals(Object obj)
String	getDataInputConfig() Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form.
String	getFramework() Identifies the framework in which the model was trained.
String	getFrameworkVersion() Specifies the framework version to use.
String	getS3Uri() The S3 path where the model artifacts, which result from model training, are stored.
int	hashCode()
void	marshall(ProtocolMarshaller protocolMarshaller) Marshalls this structured data using the given ProtocolMarshaller.
void	setDataInputConfig(String dataInputConfig) Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form.
void	setFramework(String framework) Identifies the framework in which the model was trained.
void	setFrameworkVersion(String frameworkVersion) Specifies the framework version to use.
void	setS3Uri(String s3Uri) The S3 path where the model artifacts, which result from model training, are stored.
String	toString() Returns a string representation of this object.
InputConfig	withDataInputConfig(String dataInputConfig) Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form.
InputConfig	withFramework(Framework framework) Identifies the framework in which the model was trained.
InputConfig	withFramework(String framework) Identifies the framework in which the model was trained.
InputConfig	withFrameworkVersion(String frameworkVersion) Specifies the framework version to use.
InputConfig	withS3Uri(String s3Uri) The S3 path where the model artifacts, which result from model training, are stored.

Methods inherited from class java.lang.Object

getClass, notify, notifyAll, wait, wait, wait

Constructor Detail

InputConfig

public InputConfig()

Method Detail

setS3Uri

public void setS3Uri(String s3Uri)

The S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix).

Parameters:

s3Uri - The S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix).

getS3Uri

public String getS3Uri()

The S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix).

Returns:

The S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix).

withS3Uri

public InputConfig withS3Uri(String s3Uri)

The S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix).

Parameters:

s3Uri - The S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix).

Returns:

Returns a reference to this object so that method calls can be chained together.

setDataInputConfig

public void setDataInputConfig(String dataInputConfig)

Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are InputConfig$Framework specific.

• TensorFlow: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.

  • Examples for one input:

    • If using the console, {"input":[1,1024,1024,3]}

    • If using the CLI, {\"input\":[1,1024,1024,3]}

  • Examples for two inputs:

    • If using the console, {"data1": [1,28,28,1], "data2":[1,28,28,1]}

    • If using the CLI, {\"data1\": [1,28,28,1], \"data2\":[1,28,28,1]}

• KERAS: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, DataInputConfig should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.

  • Examples for one input:

    • If using the console, {"input_1":[1,3,224,224]}

    • If using the CLI, {\"input_1\":[1,3,224,224]}

  • Examples for two inputs:

    • If using the console, {"input_1": [1,3,224,224], "input_2":[1,3,224,224]}

    • If using the CLI, {\"input_1\": [1,3,224,224], \"input_2\":[1,3,224,224]}

• MXNET/ONNX/DARKNET: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.

  • Examples for one input:

    • If using the console, {"data":[1,3,1024,1024]}

    • If using the CLI, {\"data\":[1,3,1024,1024]}

  • Examples for two inputs:

    • If using the console, {"var1": [1,1,28,28], "var2":[1,1,28,28]}

    • If using the CLI, {\"var1\": [1,1,28,28], \"var2\":[1,1,28,28]}

• PyTorch: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.

  • Examples for one input in dictionary format:

    • If using the console, {"input0":[1,3,224,224]}

    • If using the CLI, {\"input0\":[1,3,224,224]}

  • Example for one input in list format: [[1,3,224,224]]

  • Examples for two inputs in dictionary format:

    • If using the console, {"input0":[1,3,224,224], "input1":[1,3,224,224]}

    • If using the CLI, {\"input0\":[1,3,224,224], \"input1\":[1,3,224,224]}

  • Example for two inputs in list format: [[1,3,224,224], [1,3,224,224]]

• XGBOOST: input data name and shape are not needed.

DataInputConfig supports the following parameters for CoreML OutputConfig$TargetDevice (ML Model format):

• shape: Input shape, for example {"input_1": {"shape": [1,224,224,3]}}. In addition to static input shapes, CoreML converter supports Flexible input shapes:

  • Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: {"input_1": {"shape": ["1..10", 224, 224, 3]}}

  • Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: {"input_1": {"shape": [[1, 224, 224, 3], [1, 160, 160, 3]]}}

• default_shape: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example {"input_1": {"shape": ["1..10", 224, 224, 3], "default_shape": [1, 224, 224, 3]}}

• type: Input type. Allowed values: Image and Tensor. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as bias and scale.

• bias: If the input type is an Image, you need to provide the bias vector.

• scale: If the input type is an Image, you need to provide a scale factor.

CoreML ClassifierConfig parameters can be specified using OutputConfig$CompilerOptions. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:

• Tensor type input:

  • "DataInputConfig": {"input_1": {"shape": [[1,224,224,3], [1,160,160,3]], "default_shape": [1,224,224,3]}}

• Tensor type input without input name (PyTorch):

  • "DataInputConfig": [{"shape": [[1,3,224,224], [1,3,160,160]], "default_shape": [1,3,224,224]}]

• Image type input:

  • "DataInputConfig": {"input_1": {"shape": [[1,224,224,3], [1,160,160,3]], "default_shape": [1,224,224,3], "type": "Image", "bias": [-1,-1,-1], "scale": 0.007843137255}}

  • "CompilerOptions": {"class_labels": "imagenet_labels_1000.txt"}

• Image type input without input name (PyTorch):

  • "DataInputConfig": [{"shape": [[1,3,224,224], [1,3,160,160]], "default_shape": [1,3,224,224], "type": "Image", "bias": [-1,-1,-1], "scale": 0.007843137255}]

  • "CompilerOptions": {"class_labels": "imagenet_labels_1000.txt"}

Depending on the model format, DataInputConfig requires the following parameters for ml_eia2 OutputConfig:TargetDevice.

• For TensorFlow models saved in the SavedModel format, specify the input names from signature_def_key and the input model shapes for DataInputConfig. Specify the signature_def_key in OutputConfig:CompilerOptions if the model does not use TensorFlow's default signature def key. For example:

  • "DataInputConfig": {"inputs": [1, 224, 224, 3]}

  • "CompilerOptions": {"signature_def_key": "serving_custom"}

• For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in DataInputConfig and the output tensor names for output_names in OutputConfig:CompilerOptions . For example:

  • "DataInputConfig": {"input_tensor:0": [1, 224, 224, 3]}

  • "CompilerOptions": {"output_names": ["output_tensor:0"]}

Parameters:

dataInputConfig - Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are InputConfig$Framework specific.

• TensorFlow: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.

  • Examples for one input:

    • If using the console, {"input":[1,1024,1024,3]}

    • If using the CLI, {\"input\":[1,1024,1024,3]}

  • Examples for two inputs:

    • If using the console, {"data1": [1,28,28,1], "data2":[1,28,28,1]}

    • If using the CLI, {\"data1\": [1,28,28,1], \"data2\":[1,28,28,1]}

• KERAS: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, DataInputConfig should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.

  • Examples for one input:

    • If using the console, {"input_1":[1,3,224,224]}

    • If using the CLI, {\"input_1\":[1,3,224,224]}

  • Examples for two inputs:

    • If using the console, {"input_1": [1,3,224,224], "input_2":[1,3,224,224]}

    • If using the CLI, {\"input_1\": [1,3,224,224], \"input_2\":[1,3,224,224]}

• MXNET/ONNX/DARKNET: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.

  • Examples for one input:

    • If using the console, {"data":[1,3,1024,1024]}

    • If using the CLI, {\"data\":[1,3,1024,1024]}

  • Examples for two inputs:

    • If using the console, {"var1": [1,1,28,28], "var2":[1,1,28,28]}

    • If using the CLI, {\"var1\": [1,1,28,28], \"var2\":[1,1,28,28]}

• PyTorch: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.

  • Examples for one input in dictionary format:

    • If using the console, {"input0":[1,3,224,224]}

    • If using the CLI, {\"input0\":[1,3,224,224]}

  • Example for one input in list format: [[1,3,224,224]]

  • Examples for two inputs in dictionary format:

    • If using the console, {"input0":[1,3,224,224], "input1":[1,3,224,224]}

    • If using the CLI, {\"input0\":[1,3,224,224], \"input1\":[1,3,224,224]}

  • Example for two inputs in list format: [[1,3,224,224], [1,3,224,224]]

• XGBOOST: input data name and shape are not needed.

DataInputConfig supports the following parameters for CoreML OutputConfig$TargetDevice (ML Model format):

• shape: Input shape, for example {"input_1": {"shape": [1,224,224,3]}}. In addition to static input shapes, CoreML converter supports Flexible input shapes:

  • Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: {"input_1": {"shape": ["1..10", 224, 224, 3]}}

  • Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: {"input_1": {"shape": [[1, 224, 224, 3], [1, 160, 160, 3]]}}

• default_shape: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example {"input_1": {"shape": ["1..10", 224, 224, 3], "default_shape": [1, 224, 224, 3]}}

• type: Input type. Allowed values: Image and Tensor. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as bias and scale.

• bias: If the input type is an Image, you need to provide the bias vector.

• scale: If the input type is an Image, you need to provide a scale factor.

CoreML ClassifierConfig parameters can be specified using OutputConfig$CompilerOptions. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:

• Tensor type input:

  • "DataInputConfig": {"input_1": {"shape": [[1,224,224,3], [1,160,160,3]], "default_shape": [1,224,224,3]}}

• Tensor type input without input name (PyTorch):

  • "DataInputConfig": [{"shape": [[1,3,224,224], [1,3,160,160]], "default_shape": [1,3,224,224]}]

• Image type input:

  • "DataInputConfig": {"input_1": {"shape": [[1,224,224,3], [1,160,160,3]], "default_shape": [1,224,224,3], "type": "Image", "bias": [-1,-1,-1], "scale": 0.007843137255}}

  • "CompilerOptions": {"class_labels": "imagenet_labels_1000.txt"}

• Image type input without input name (PyTorch):

  • "DataInputConfig": [{"shape": [[1,3,224,224], [1,3,160,160]], "default_shape": [1,3,224,224], "type": "Image", "bias": [-1,-1,-1], "scale": 0.007843137255}]

  • "CompilerOptions": {"class_labels": "imagenet_labels_1000.txt"}

Depending on the model format, DataInputConfig requires the following parameters for ml_eia2 OutputConfig:TargetDevice.

• For TensorFlow models saved in the SavedModel format, specify the input names from signature_def_key and the input model shapes for DataInputConfig. Specify the signature_def_key in OutputConfig:CompilerOptions if the model does not use TensorFlow's default signature def key. For example:

  • "DataInputConfig": {"inputs": [1, 224, 224, 3]}

  • "CompilerOptions": {"signature_def_key": "serving_custom"}

• For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in DataInputConfig and the output tensor names for output_names in OutputConfig:CompilerOptions . For example:

  • "DataInputConfig": {"input_tensor:0": [1, 224, 224, 3]}

  • "CompilerOptions": {"output_names": ["output_tensor:0"]}

getDataInputConfig

public String getDataInputConfig()

Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are InputConfig$Framework specific.

• TensorFlow: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.

  • Examples for one input:

    • If using the console, {"input":[1,1024,1024,3]}

    • If using the CLI, {\"input\":[1,1024,1024,3]}

  • Examples for two inputs:

    • If using the console, {"data1": [1,28,28,1], "data2":[1,28,28,1]}

    • If using the CLI, {\"data1\": [1,28,28,1], \"data2\":[1,28,28,1]}

• KERAS: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, DataInputConfig should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.

  • Examples for one input:

    • If using the console, {"input_1":[1,3,224,224]}

    • If using the CLI, {\"input_1\":[1,3,224,224]}

  • Examples for two inputs:

    • If using the console, {"input_1": [1,3,224,224], "input_2":[1,3,224,224]}

    • If using the CLI, {\"input_1\": [1,3,224,224], \"input_2\":[1,3,224,224]}

• MXNET/ONNX/DARKNET: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.

  • Examples for one input:

    • If using the console, {"data":[1,3,1024,1024]}

    • If using the CLI, {\"data\":[1,3,1024,1024]}

  • Examples for two inputs:

    • If using the console, {"var1": [1,1,28,28], "var2":[1,1,28,28]}

    • If using the CLI, {\"var1\": [1,1,28,28], \"var2\":[1,1,28,28]}

• PyTorch: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.

  • Examples for one input in dictionary format:

    • If using the console, {"input0":[1,3,224,224]}

    • If using the CLI, {\"input0\":[1,3,224,224]}

  • Example for one input in list format: [[1,3,224,224]]

  • Examples for two inputs in dictionary format:

    • If using the console, {"input0":[1,3,224,224], "input1":[1,3,224,224]}

    • If using the CLI, {\"input0\":[1,3,224,224], \"input1\":[1,3,224,224]}

  • Example for two inputs in list format: [[1,3,224,224], [1,3,224,224]]

• XGBOOST: input data name and shape are not needed.

DataInputConfig supports the following parameters for CoreML OutputConfig$TargetDevice (ML Model format):

• shape: Input shape, for example {"input_1": {"shape": [1,224,224,3]}}. In addition to static input shapes, CoreML converter supports Flexible input shapes:

  • Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: {"input_1": {"shape": ["1..10", 224, 224, 3]}}

  • Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: {"input_1": {"shape": [[1, 224, 224, 3], [1, 160, 160, 3]]}}

• default_shape: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example {"input_1": {"shape": ["1..10", 224, 224, 3], "default_shape": [1, 224, 224, 3]}}

• type: Input type. Allowed values: Image and Tensor. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as bias and scale.

• bias: If the input type is an Image, you need to provide the bias vector.

• scale: If the input type is an Image, you need to provide a scale factor.

CoreML ClassifierConfig parameters can be specified using OutputConfig$CompilerOptions. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:

• Tensor type input:

  • "DataInputConfig": {"input_1": {"shape": [[1,224,224,3], [1,160,160,3]], "default_shape": [1,224,224,3]}}

• Tensor type input without input name (PyTorch):

  • "DataInputConfig": [{"shape": [[1,3,224,224], [1,3,160,160]], "default_shape": [1,3,224,224]}]

• Image type input:

  • "DataInputConfig": {"input_1": {"shape": [[1,224,224,3], [1,160,160,3]], "default_shape": [1,224,224,3], "type": "Image", "bias": [-1,-1,-1], "scale": 0.007843137255}}

  • "CompilerOptions": {"class_labels": "imagenet_labels_1000.txt"}

• Image type input without input name (PyTorch):

  • "DataInputConfig": [{"shape": [[1,3,224,224], [1,3,160,160]], "default_shape": [1,3,224,224], "type": "Image", "bias": [-1,-1,-1], "scale": 0.007843137255}]

  • "CompilerOptions": {"class_labels": "imagenet_labels_1000.txt"}

Depending on the model format, DataInputConfig requires the following parameters for ml_eia2 OutputConfig:TargetDevice.

• For TensorFlow models saved in the SavedModel format, specify the input names from signature_def_key and the input model shapes for DataInputConfig. Specify the signature_def_key in OutputConfig:CompilerOptions if the model does not use TensorFlow's default signature def key. For example:

  • "DataInputConfig": {"inputs": [1, 224, 224, 3]}

  • "CompilerOptions": {"signature_def_key": "serving_custom"}

• For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in DataInputConfig and the output tensor names for output_names in OutputConfig:CompilerOptions . For example:

  • "DataInputConfig": {"input_tensor:0": [1, 224, 224, 3]}

  • "CompilerOptions": {"output_names": ["output_tensor:0"]}

Returns:

Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are InputConfig$Framework specific.

• TensorFlow: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.

  • Examples for one input:

    • If using the console, {"input":[1,1024,1024,3]}

    • If using the CLI, {\"input\":[1,1024,1024,3]}

  • Examples for two inputs:

    • If using the console, {"data1": [1,28,28,1], "data2":[1,28,28,1]}

    • If using the CLI, {\"data1\": [1,28,28,1], \"data2\":[1,28,28,1]}

• KERAS: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, DataInputConfig should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.

  • Examples for one input:

    • If using the console, {"input_1":[1,3,224,224]}

    • If using the CLI, {\"input_1\":[1,3,224,224]}

  • Examples for two inputs:

    • If using the console, {"input_1": [1,3,224,224], "input_2":[1,3,224,224]}

    • If using the CLI, {\"input_1\": [1,3,224,224], \"input_2\":[1,3,224,224]}

• MXNET/ONNX/DARKNET: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.

  • Examples for one input:

    • If using the console, {"data":[1,3,1024,1024]}

    • If using the CLI, {\"data\":[1,3,1024,1024]}

  • Examples for two inputs:

    • If using the console, {"var1": [1,1,28,28], "var2":[1,1,28,28]}

    • If using the CLI, {\"var1\": [1,1,28,28], \"var2\":[1,1,28,28]}

• PyTorch: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.

  • Examples for one input in dictionary format:

    • If using the console, {"input0":[1,3,224,224]}

    • If using the CLI, {\"input0\":[1,3,224,224]}

  • Example for one input in list format: [[1,3,224,224]]

  • Examples for two inputs in dictionary format:

    • If using the console, {"input0":[1,3,224,224], "input1":[1,3,224,224]}

    • If using the CLI, {\"input0\":[1,3,224,224], \"input1\":[1,3,224,224]}

  • Example for two inputs in list format: [[1,3,224,224], [1,3,224,224]]

• XGBOOST: input data name and shape are not needed.

DataInputConfig supports the following parameters for CoreML OutputConfig$TargetDevice (ML Model format):

• shape: Input shape, for example {"input_1": {"shape": [1,224,224,3]}}. In addition to static input shapes, CoreML converter supports Flexible input shapes:

  • Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: {"input_1": {"shape": ["1..10", 224, 224, 3]}}

  • Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: {"input_1": {"shape": [[1, 224, 224, 3], [1, 160, 160, 3]]}}

• default_shape: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example {"input_1": {"shape": ["1..10", 224, 224, 3], "default_shape": [1, 224, 224, 3]}}

• type: Input type. Allowed values: Image and Tensor. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as bias and scale.

• bias: If the input type is an Image, you need to provide the bias vector.

• scale: If the input type is an Image, you need to provide a scale factor.

CoreML ClassifierConfig parameters can be specified using OutputConfig$CompilerOptions. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:

• Tensor type input:

  • "DataInputConfig": {"input_1": {"shape": [[1,224,224,3], [1,160,160,3]], "default_shape": [1,224,224,3]}}

• Tensor type input without input name (PyTorch):

  • "DataInputConfig": [{"shape": [[1,3,224,224], [1,3,160,160]], "default_shape": [1,3,224,224]}]

• Image type input:

  • "DataInputConfig": {"input_1": {"shape": [[1,224,224,3], [1,160,160,3]], "default_shape": [1,224,224,3], "type": "Image", "bias": [-1,-1,-1], "scale": 0.007843137255}}

  • "CompilerOptions": {"class_labels": "imagenet_labels_1000.txt"}

• Image type input without input name (PyTorch):

  • "DataInputConfig": [{"shape": [[1,3,224,224], [1,3,160,160]], "default_shape": [1,3,224,224], "type": "Image", "bias": [-1,-1,-1], "scale": 0.007843137255}]

  • "CompilerOptions": {"class_labels": "imagenet_labels_1000.txt"}

Depending on the model format, DataInputConfig requires the following parameters for ml_eia2 OutputConfig:TargetDevice.

• For TensorFlow models saved in the SavedModel format, specify the input names from signature_def_key and the input model shapes for DataInputConfig. Specify the signature_def_key in OutputConfig:CompilerOptions if the model does not use TensorFlow's default signature def key. For example:

  • "DataInputConfig": {"inputs": [1, 224, 224, 3]}

  • "CompilerOptions": {"signature_def_key": "serving_custom"}

• For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in DataInputConfig and the output tensor names for output_names in OutputConfig:CompilerOptions . For example:

  • "DataInputConfig": {"input_tensor:0": [1, 224, 224, 3]}

  • "CompilerOptions": {"output_names": ["output_tensor:0"]}

withDataInputConfig

public InputConfig withDataInputConfig(String dataInputConfig)

Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are InputConfig$Framework specific.

• TensorFlow: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.

  • Examples for one input:

    • If using the console, {"input":[1,1024,1024,3]}

    • If using the CLI, {\"input\":[1,1024,1024,3]}

  • Examples for two inputs:

    • If using the console, {"data1": [1,28,28,1], "data2":[1,28,28,1]}

    • If using the CLI, {\"data1\": [1,28,28,1], \"data2\":[1,28,28,1]}

• KERAS: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, DataInputConfig should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.

  • Examples for one input:

    • If using the console, {"input_1":[1,3,224,224]}

    • If using the CLI, {\"input_1\":[1,3,224,224]}

  • Examples for two inputs:

    • If using the console, {"input_1": [1,3,224,224], "input_2":[1,3,224,224]}

    • If using the CLI, {\"input_1\": [1,3,224,224], \"input_2\":[1,3,224,224]}

• MXNET/ONNX/DARKNET: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.

  • Examples for one input:

    • If using the console, {"data":[1,3,1024,1024]}

    • If using the CLI, {\"data\":[1,3,1024,1024]}

  • Examples for two inputs:

    • If using the console, {"var1": [1,1,28,28], "var2":[1,1,28,28]}

    • If using the CLI, {\"var1\": [1,1,28,28], \"var2\":[1,1,28,28]}

• PyTorch: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.

  • Examples for one input in dictionary format:

    • If using the console, {"input0":[1,3,224,224]}

    • If using the CLI, {\"input0\":[1,3,224,224]}

  • Example for one input in list format: [[1,3,224,224]]

  • Examples for two inputs in dictionary format:

    • If using the console, {"input0":[1,3,224,224], "input1":[1,3,224,224]}

    • If using the CLI, {\"input0\":[1,3,224,224], \"input1\":[1,3,224,224]}

  • Example for two inputs in list format: [[1,3,224,224], [1,3,224,224]]

• XGBOOST: input data name and shape are not needed.

DataInputConfig supports the following parameters for CoreML OutputConfig$TargetDevice (ML Model format):

• shape: Input shape, for example {"input_1": {"shape": [1,224,224,3]}}. In addition to static input shapes, CoreML converter supports Flexible input shapes:

  • Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: {"input_1": {"shape": ["1..10", 224, 224, 3]}}

  • Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: {"input_1": {"shape": [[1, 224, 224, 3], [1, 160, 160, 3]]}}

• default_shape: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example {"input_1": {"shape": ["1..10", 224, 224, 3], "default_shape": [1, 224, 224, 3]}}

• type: Input type. Allowed values: Image and Tensor. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as bias and scale.

• bias: If the input type is an Image, you need to provide the bias vector.

• scale: If the input type is an Image, you need to provide a scale factor.

CoreML ClassifierConfig parameters can be specified using OutputConfig$CompilerOptions. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:

• Tensor type input:

  • "DataInputConfig": {"input_1": {"shape": [[1,224,224,3], [1,160,160,3]], "default_shape": [1,224,224,3]}}

• Tensor type input without input name (PyTorch):

  • "DataInputConfig": [{"shape": [[1,3,224,224], [1,3,160,160]], "default_shape": [1,3,224,224]}]

• Image type input:

  • "DataInputConfig": {"input_1": {"shape": [[1,224,224,3], [1,160,160,3]], "default_shape": [1,224,224,3], "type": "Image", "bias": [-1,-1,-1], "scale": 0.007843137255}}

  • "CompilerOptions": {"class_labels": "imagenet_labels_1000.txt"}

• Image type input without input name (PyTorch):

  • "DataInputConfig": [{"shape": [[1,3,224,224], [1,3,160,160]], "default_shape": [1,3,224,224], "type": "Image", "bias": [-1,-1,-1], "scale": 0.007843137255}]

  • "CompilerOptions": {"class_labels": "imagenet_labels_1000.txt"}

Depending on the model format, DataInputConfig requires the following parameters for ml_eia2 OutputConfig:TargetDevice.

• For TensorFlow models saved in the SavedModel format, specify the input names from signature_def_key and the input model shapes for DataInputConfig. Specify the signature_def_key in OutputConfig:CompilerOptions if the model does not use TensorFlow's default signature def key. For example:

  • "DataInputConfig": {"inputs": [1, 224, 224, 3]}

  • "CompilerOptions": {"signature_def_key": "serving_custom"}

• For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in DataInputConfig and the output tensor names for output_names in OutputConfig:CompilerOptions . For example:

  • "DataInputConfig": {"input_tensor:0": [1, 224, 224, 3]}

  • "CompilerOptions": {"output_names": ["output_tensor:0"]}

Parameters:

dataInputConfig - Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are InputConfig$Framework specific.

• TensorFlow: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.

  • Examples for one input:

    • If using the console, {"input":[1,1024,1024,3]}

    • If using the CLI, {\"input\":[1,1024,1024,3]}

  • Examples for two inputs:

    • If using the console, {"data1": [1,28,28,1], "data2":[1,28,28,1]}

    • If using the CLI, {\"data1\": [1,28,28,1], \"data2\":[1,28,28,1]}

• KERAS: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, DataInputConfig should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.

  • Examples for one input:

    • If using the console, {"input_1":[1,3,224,224]}

    • If using the CLI, {\"input_1\":[1,3,224,224]}

  • Examples for two inputs:

    • If using the console, {"input_1": [1,3,224,224], "input_2":[1,3,224,224]}

    • If using the CLI, {\"input_1\": [1,3,224,224], \"input_2\":[1,3,224,224]}

• MXNET/ONNX/DARKNET: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.

  • Examples for one input:

    • If using the console, {"data":[1,3,1024,1024]}

    • If using the CLI, {\"data\":[1,3,1024,1024]}

  • Examples for two inputs:

    • If using the console, {"var1": [1,1,28,28], "var2":[1,1,28,28]}

    • If using the CLI, {\"var1\": [1,1,28,28], \"var2\":[1,1,28,28]}

• PyTorch: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.

  • Examples for one input in dictionary format:

    • If using the console, {"input0":[1,3,224,224]}

    • If using the CLI, {\"input0\":[1,3,224,224]}

  • Example for one input in list format: [[1,3,224,224]]

  • Examples for two inputs in dictionary format:

    • If using the console, {"input0":[1,3,224,224], "input1":[1,3,224,224]}

    • If using the CLI, {\"input0\":[1,3,224,224], \"input1\":[1,3,224,224]}

  • Example for two inputs in list format: [[1,3,224,224], [1,3,224,224]]

• XGBOOST: input data name and shape are not needed.

DataInputConfig supports the following parameters for CoreML OutputConfig$TargetDevice (ML Model format):

• shape: Input shape, for example {"input_1": {"shape": [1,224,224,3]}}. In addition to static input shapes, CoreML converter supports Flexible input shapes:

  • Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: {"input_1": {"shape": ["1..10", 224, 224, 3]}}

  • Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: {"input_1": {"shape": [[1, 224, 224, 3], [1, 160, 160, 3]]}}

• default_shape: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example {"input_1": {"shape": ["1..10", 224, 224, 3], "default_shape": [1, 224, 224, 3]}}

• type: Input type. Allowed values: Image and Tensor. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as bias and scale.

• bias: If the input type is an Image, you need to provide the bias vector.

• scale: If the input type is an Image, you need to provide a scale factor.

CoreML ClassifierConfig parameters can be specified using OutputConfig$CompilerOptions. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:

• Tensor type input:

  • "DataInputConfig": {"input_1": {"shape": [[1,224,224,3], [1,160,160,3]], "default_shape": [1,224,224,3]}}

• Tensor type input without input name (PyTorch):

  • "DataInputConfig": [{"shape": [[1,3,224,224], [1,3,160,160]], "default_shape": [1,3,224,224]}]

• Image type input:

  • "DataInputConfig": {"input_1": {"shape": [[1,224,224,3], [1,160,160,3]], "default_shape": [1,224,224,3], "type": "Image", "bias": [-1,-1,-1], "scale": 0.007843137255}}

  • "CompilerOptions": {"class_labels": "imagenet_labels_1000.txt"}

• Image type input without input name (PyTorch):

  • "DataInputConfig": [{"shape": [[1,3,224,224], [1,3,160,160]], "default_shape": [1,3,224,224], "type": "Image", "bias": [-1,-1,-1], "scale": 0.007843137255}]

  • "CompilerOptions": {"class_labels": "imagenet_labels_1000.txt"}

Depending on the model format, DataInputConfig requires the following parameters for ml_eia2 OutputConfig:TargetDevice.

• For TensorFlow models saved in the SavedModel format, specify the input names from signature_def_key and the input model shapes for DataInputConfig. Specify the signature_def_key in OutputConfig:CompilerOptions if the model does not use TensorFlow's default signature def key. For example:

  • "DataInputConfig": {"inputs": [1, 224, 224, 3]}

  • "CompilerOptions": {"signature_def_key": "serving_custom"}

• For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in DataInputConfig and the output tensor names for output_names in OutputConfig:CompilerOptions . For example:

  • "DataInputConfig": {"input_tensor:0": [1, 224, 224, 3]}

  • "CompilerOptions": {"output_names": ["output_tensor:0"]}

Returns:

Returns a reference to this object so that method calls can be chained together.

setFramework

public void setFramework(String framework)

Identifies the framework in which the model was trained. For example: TENSORFLOW.

Parameters:

framework - Identifies the framework in which the model was trained. For example: TENSORFLOW.

See Also:

Framework

getFramework

public String getFramework()

Identifies the framework in which the model was trained. For example: TENSORFLOW.

Returns:

Identifies the framework in which the model was trained. For example: TENSORFLOW.

See Also:

Framework

withFramework

public InputConfig withFramework(String framework)

Identifies the framework in which the model was trained. For example: TENSORFLOW.

Parameters:

framework - Identifies the framework in which the model was trained. For example: TENSORFLOW.

Returns:

Returns a reference to this object so that method calls can be chained together.

See Also:

Framework

withFramework

public InputConfig withFramework(Framework framework)

Identifies the framework in which the model was trained. For example: TENSORFLOW.

Parameters:

framework - Identifies the framework in which the model was trained. For example: TENSORFLOW.

Returns:

Returns a reference to this object so that method calls can be chained together.

See Also:

Framework

setFrameworkVersion

public void setFrameworkVersion(String frameworkVersion)

Specifies the framework version to use.

This API field is only supported for PyTorch framework versions 1.4, 1.5, and 1.6 for cloud instance target devices: ml_c4, ml_c5, ml_m4, ml_m5, ml_p2, ml_p3, and ml_g4dn.

Parameters:

frameworkVersion - Specifies the framework version to use.

This API field is only supported for PyTorch framework versions 1.4, 1.5, and 1.6 for cloud instance target devices: ml_c4, ml_c5, ml_m4, ml_m5, ml_p2, ml_p3, and ml_g4dn.

getFrameworkVersion

public String getFrameworkVersion()

Specifies the framework version to use.

This API field is only supported for PyTorch framework versions 1.4, 1.5, and 1.6 for cloud instance target devices: ml_c4, ml_c5, ml_m4, ml_m5, ml_p2, ml_p3, and ml_g4dn.

Returns:

Specifies the framework version to use.

This API field is only supported for PyTorch framework versions 1.4, 1.5, and 1.6 for cloud instance target devices: ml_c4, ml_c5, ml_m4, ml_m5, ml_p2, ml_p3, and ml_g4dn.

withFrameworkVersion

public InputConfig withFrameworkVersion(String frameworkVersion)

Specifies the framework version to use.

This API field is only supported for PyTorch framework versions 1.4, 1.5, and 1.6 for cloud instance target devices: ml_c4, ml_c5, ml_m4, ml_m5, ml_p2, ml_p3, and ml_g4dn.

Parameters:

frameworkVersion - Specifies the framework version to use.

This API field is only supported for PyTorch framework versions 1.4, 1.5, and 1.6 for cloud instance target devices: ml_c4, ml_c5, ml_m4, ml_m5, ml_p2, ml_p3, and ml_g4dn.

Returns:

Returns a reference to this object so that method calls can be chained together.

toString

public String toString()

Returns a string representation of this object. This is useful for testing and debugging. Sensitive data will be redacted from this string using a placeholder value.

Overrides:

toString in class Object

Returns:

A string representation of this object.

See Also:

Object.toString()

equals

public boolean equals(Object obj)

Overrides:

equals in class Object

hashCode

public int hashCode()

Overrides:

hashCode in class Object

clone

public InputConfig clone()

Overrides:

clone in class Object

marshall

public void marshall(ProtocolMarshaller protocolMarshaller)

Description copied from interface: StructuredPojo

Marshalls this structured data using the given ProtocolMarshaller.

Specified by:

marshall in interface StructuredPojo

Parameters:

protocolMarshaller - Implementation of ProtocolMarshaller used to marshall this object's data.