{-# LANGUAGE DeriveGeneric #-} {-# LANGUAGE DuplicateRecordFields #-} {-# LANGUAGE NamedFieldPuns #-} {-# LANGUAGE OverloadedStrings #-} {-# LANGUAGE RecordWildCards #-} {-# LANGUAGE StrictData #-} {-# LANGUAGE NoImplicitPrelude #-} {-# OPTIONS_GHC -fno-warn-unused-imports #-} {-# OPTIONS_GHC -fno-warn-unused-matches #-} -- Derived from AWS service descriptions, licensed under Apache 2.0. -- | -- Module : Amazonka.SageMaker.Types.InputConfig -- Copyright : (c) 2013-2021 Brendan Hay -- License : Mozilla Public License, v. 2.0. -- Maintainer : Brendan Hay <brendan.g.hay+amazonka@gmail.com> -- Stability : auto-generated -- Portability : non-portable (GHC extensions) module Amazonka.SageMaker.Types.InputConfig where import qualified Amazonka.Core as Core import qualified Amazonka.Lens as Lens import qualified Amazonka.Prelude as Prelude import Amazonka.SageMaker.Types.Framework -- | 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:/ 'newInputConfig' smart constructor. data InputConfig = InputConfig' { -- | 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@. InputConfig -> Maybe Text frameworkVersion :: Prelude.Maybe Prelude.Text, -- | 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). InputConfig -> Text s3Uri :: Prelude.Text, -- | 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@ -- <https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice 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 -- <https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions 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 -- <https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions OutputConfig:CompilerOptions> -- . For example: -- -- - @\"DataInputConfig\": {\"input_tensor:0\": [1, 224, 224, 3]}@ -- -- - @\"CompilerOptions\": {\"output_names\": [\"output_tensor:0\"]}@ InputConfig -> Text dataInputConfig :: Prelude.Text, -- | Identifies the framework in which the model was trained. For example: -- TENSORFLOW. InputConfig -> Framework framework :: Framework } deriving (InputConfig -> InputConfig -> Bool (InputConfig -> InputConfig -> Bool) -> (InputConfig -> InputConfig -> Bool) -> Eq InputConfig forall a. (a -> a -> Bool) -> (a -> a -> Bool) -> Eq a /= :: InputConfig -> InputConfig -> Bool $c/= :: InputConfig -> InputConfig -> Bool == :: InputConfig -> InputConfig -> Bool $c== :: InputConfig -> InputConfig -> Bool Prelude.Eq, ReadPrec [InputConfig] ReadPrec InputConfig Int -> ReadS InputConfig ReadS [InputConfig] (Int -> ReadS InputConfig) -> ReadS [InputConfig] -> ReadPrec InputConfig -> ReadPrec [InputConfig] -> Read InputConfig forall a. (Int -> ReadS a) -> ReadS [a] -> ReadPrec a -> ReadPrec [a] -> Read a readListPrec :: ReadPrec [InputConfig] $creadListPrec :: ReadPrec [InputConfig] readPrec :: ReadPrec InputConfig $creadPrec :: ReadPrec InputConfig readList :: ReadS [InputConfig] $creadList :: ReadS [InputConfig] readsPrec :: Int -> ReadS InputConfig $creadsPrec :: Int -> ReadS InputConfig Prelude.Read, Int -> InputConfig -> ShowS [InputConfig] -> ShowS InputConfig -> String (Int -> InputConfig -> ShowS) -> (InputConfig -> String) -> ([InputConfig] -> ShowS) -> Show InputConfig forall a. (Int -> a -> ShowS) -> (a -> String) -> ([a] -> ShowS) -> Show a showList :: [InputConfig] -> ShowS $cshowList :: [InputConfig] -> ShowS show :: InputConfig -> String $cshow :: InputConfig -> String showsPrec :: Int -> InputConfig -> ShowS $cshowsPrec :: Int -> InputConfig -> ShowS Prelude.Show, (forall x. InputConfig -> Rep InputConfig x) -> (forall x. Rep InputConfig x -> InputConfig) -> Generic InputConfig forall x. Rep InputConfig x -> InputConfig forall x. InputConfig -> Rep InputConfig x forall a. (forall x. a -> Rep a x) -> (forall x. Rep a x -> a) -> Generic a $cto :: forall x. Rep InputConfig x -> InputConfig $cfrom :: forall x. InputConfig -> Rep InputConfig x Prelude.Generic) -- | -- Create a value of 'InputConfig' with all optional fields omitted. -- -- Use <https://hackage.haskell.org/package/generic-lens generic-lens> or <https://hackage.haskell.org/package/optics optics> to modify other optional fields. -- -- The following record fields are available, with the corresponding lenses provided -- for backwards compatibility: -- -- 'frameworkVersion', 'inputConfig_frameworkVersion' - Specifies the framework version to use. -- -- This API field is only supported for PyTorch framework versions @1.4@, -- @1.5@, and @1.6@ for cloud instance target devices: @ml_c4@, @ml_c5@, -- @ml_m4@, @ml_m5@, @ml_p2@, @ml_p3@, and @ml_g4dn@. -- -- 's3Uri', 'inputConfig_s3Uri' - The S3 path where the model artifacts, which result from model training, -- are stored. This path must point to a single gzip compressed tar archive -- (.tar.gz suffix). -- -- 'dataInputConfig', 'inputConfig_dataInputConfig' - Specifies the name and shape of the expected data inputs for your -- trained model with a JSON dictionary form. The data inputs are -- InputConfig$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@ -- <https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice 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 -- <https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions 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 -- <https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions OutputConfig:CompilerOptions> -- . For example: -- -- - @\"DataInputConfig\": {\"input_tensor:0\": [1, 224, 224, 3]}@ -- -- - @\"CompilerOptions\": {\"output_names\": [\"output_tensor:0\"]}@ -- -- 'framework', 'inputConfig_framework' - Identifies the framework in which the model was trained. For example: -- TENSORFLOW. newInputConfig :: -- | 's3Uri' Prelude.Text -> -- | 'dataInputConfig' Prelude.Text -> -- | 'framework' Framework -> InputConfig newInputConfig :: Text -> Text -> Framework -> InputConfig newInputConfig Text pS3Uri_ Text pDataInputConfig_ Framework pFramework_ = InputConfig' :: Maybe Text -> Text -> Text -> Framework -> InputConfig InputConfig' { $sel:frameworkVersion:InputConfig' :: Maybe Text frameworkVersion = Maybe Text forall a. Maybe a Prelude.Nothing, $sel:s3Uri:InputConfig' :: Text s3Uri = Text pS3Uri_, $sel:dataInputConfig:InputConfig' :: Text dataInputConfig = Text pDataInputConfig_, $sel:framework:InputConfig' :: Framework framework = Framework pFramework_ } -- | 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@. inputConfig_frameworkVersion :: Lens.Lens' InputConfig (Prelude.Maybe Prelude.Text) inputConfig_frameworkVersion :: (Maybe Text -> f (Maybe Text)) -> InputConfig -> f InputConfig inputConfig_frameworkVersion = (InputConfig -> Maybe Text) -> (InputConfig -> Maybe Text -> InputConfig) -> Lens InputConfig InputConfig (Maybe Text) (Maybe Text) forall s a b t. (s -> a) -> (s -> b -> t) -> Lens s t a b Lens.lens (\InputConfig' {Maybe Text frameworkVersion :: Maybe Text $sel:frameworkVersion:InputConfig' :: InputConfig -> Maybe Text frameworkVersion} -> Maybe Text frameworkVersion) (\s :: InputConfig s@InputConfig' {} Maybe Text a -> InputConfig s {$sel:frameworkVersion:InputConfig' :: Maybe Text frameworkVersion = Maybe Text a} :: InputConfig) -- | 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). inputConfig_s3Uri :: Lens.Lens' InputConfig Prelude.Text inputConfig_s3Uri :: (Text -> f Text) -> InputConfig -> f InputConfig inputConfig_s3Uri = (InputConfig -> Text) -> (InputConfig -> Text -> InputConfig) -> Lens InputConfig InputConfig Text Text forall s a b t. (s -> a) -> (s -> b -> t) -> Lens s t a b Lens.lens (\InputConfig' {Text s3Uri :: Text $sel:s3Uri:InputConfig' :: InputConfig -> Text s3Uri} -> Text s3Uri) (\s :: InputConfig s@InputConfig' {} Text a -> InputConfig s {$sel:s3Uri:InputConfig' :: Text s3Uri = Text a} :: InputConfig) -- | 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@ -- <https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice 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 -- <https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions 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 -- <https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions OutputConfig:CompilerOptions> -- . For example: -- -- - @\"DataInputConfig\": {\"input_tensor:0\": [1, 224, 224, 3]}@ -- -- - @\"CompilerOptions\": {\"output_names\": [\"output_tensor:0\"]}@ inputConfig_dataInputConfig :: Lens.Lens' InputConfig Prelude.Text inputConfig_dataInputConfig :: (Text -> f Text) -> InputConfig -> f InputConfig inputConfig_dataInputConfig = (InputConfig -> Text) -> (InputConfig -> Text -> InputConfig) -> Lens InputConfig InputConfig Text Text forall s a b t. (s -> a) -> (s -> b -> t) -> Lens s t a b Lens.lens (\InputConfig' {Text dataInputConfig :: Text $sel:dataInputConfig:InputConfig' :: InputConfig -> Text dataInputConfig} -> Text dataInputConfig) (\s :: InputConfig s@InputConfig' {} Text a -> InputConfig s {$sel:dataInputConfig:InputConfig' :: Text dataInputConfig = Text a} :: InputConfig) -- | Identifies the framework in which the model was trained. For example: -- TENSORFLOW. inputConfig_framework :: Lens.Lens' InputConfig Framework inputConfig_framework :: (Framework -> f Framework) -> InputConfig -> f InputConfig inputConfig_framework = (InputConfig -> Framework) -> (InputConfig -> Framework -> InputConfig) -> Lens InputConfig InputConfig Framework Framework forall s a b t. (s -> a) -> (s -> b -> t) -> Lens s t a b Lens.lens (\InputConfig' {Framework framework :: Framework $sel:framework:InputConfig' :: InputConfig -> Framework framework} -> Framework framework) (\s :: InputConfig s@InputConfig' {} Framework a -> InputConfig s {$sel:framework:InputConfig' :: Framework framework = Framework a} :: InputConfig) instance Core.FromJSON InputConfig where parseJSON :: Value -> Parser InputConfig parseJSON = String -> (Object -> Parser InputConfig) -> Value -> Parser InputConfig forall a. String -> (Object -> Parser a) -> Value -> Parser a Core.withObject String "InputConfig" ( \Object x -> Maybe Text -> Text -> Text -> Framework -> InputConfig InputConfig' (Maybe Text -> Text -> Text -> Framework -> InputConfig) -> Parser (Maybe Text) -> Parser (Text -> Text -> Framework -> InputConfig) forall (f :: * -> *) a b. Functor f => (a -> b) -> f a -> f b Prelude.<$> (Object x Object -> Text -> Parser (Maybe Text) forall a. FromJSON a => Object -> Text -> Parser (Maybe a) Core..:? Text "FrameworkVersion") Parser (Text -> Text -> Framework -> InputConfig) -> Parser Text -> Parser (Text -> Framework -> InputConfig) forall (f :: * -> *) a b. Applicative f => f (a -> b) -> f a -> f b Prelude.<*> (Object x Object -> Text -> Parser Text forall a. FromJSON a => Object -> Text -> Parser a Core..: Text "S3Uri") Parser (Text -> Framework -> InputConfig) -> Parser Text -> Parser (Framework -> InputConfig) forall (f :: * -> *) a b. Applicative f => f (a -> b) -> f a -> f b Prelude.<*> (Object x Object -> Text -> Parser Text forall a. FromJSON a => Object -> Text -> Parser a Core..: Text "DataInputConfig") Parser (Framework -> InputConfig) -> Parser Framework -> Parser InputConfig forall (f :: * -> *) a b. Applicative f => f (a -> b) -> f a -> f b Prelude.<*> (Object x Object -> Text -> Parser Framework forall a. FromJSON a => Object -> Text -> Parser a Core..: Text "Framework") ) instance Prelude.Hashable InputConfig instance Prelude.NFData InputConfig instance Core.ToJSON InputConfig where toJSON :: InputConfig -> Value toJSON InputConfig' {Maybe Text Text Framework framework :: Framework dataInputConfig :: Text s3Uri :: Text frameworkVersion :: Maybe Text $sel:framework:InputConfig' :: InputConfig -> Framework $sel:dataInputConfig:InputConfig' :: InputConfig -> Text $sel:s3Uri:InputConfig' :: InputConfig -> Text $sel:frameworkVersion:InputConfig' :: InputConfig -> Maybe Text ..} = [Pair] -> Value Core.object ( [Maybe Pair] -> [Pair] forall a. [Maybe a] -> [a] Prelude.catMaybes [ (Text "FrameworkVersion" Text -> Text -> Pair forall kv v. (KeyValue kv, ToJSON v) => Text -> v -> kv Core..=) (Text -> Pair) -> Maybe Text -> Maybe Pair forall (f :: * -> *) a b. Functor f => (a -> b) -> f a -> f b Prelude.<$> Maybe Text frameworkVersion, Pair -> Maybe Pair forall a. a -> Maybe a Prelude.Just (Text "S3Uri" Text -> Text -> Pair forall kv v. (KeyValue kv, ToJSON v) => Text -> v -> kv Core..= Text s3Uri), Pair -> Maybe Pair forall a. a -> Maybe a Prelude.Just (Text "DataInputConfig" Text -> Text -> Pair forall kv v. (KeyValue kv, ToJSON v) => Text -> v -> kv Core..= Text dataInputConfig), Pair -> Maybe Pair forall a. a -> Maybe a Prelude.Just (Text "Framework" Text -> Framework -> Pair forall kv v. (KeyValue kv, ToJSON v) => Text -> v -> kv Core..= Framework framework) ] )