edgeimpulse-api 1.96.2__tar.gz → 1.96.3__tar.gz

{edgeimpulse_api-1.96.2 → edgeimpulse_api-1.96.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: edgeimpulse-api
-Version: 1.96.2
+Version: 1.96.3
 Summary: Python bindings for the Edge Impulse API.
 Home-page: https://edgeimpulse.com
 License: BSD-3-Clause-Clear

{edgeimpulse_api-1.96.2 → edgeimpulse_api-1.96.3}/edgeimpulse_api/__init__.py

@@ -14,7 +14,7 @@
 
 from __future__ import absolute_import
 
-__version__ = "1.96.2" #DO_NOT_CHANGE_REPLACED_BY_BUILD_SCRIPT
+__version__ = "1.96.3" #DO_NOT_CHANGE_REPLACED_BY_BUILD_SCRIPT
 
 # import apis into sdk package
 from edgeimpulse_api.api.classify_api import ClassifyApi
@@ -390,6 +390,8 @@ from edgeimpulse_api.models.find_segment_sample_request import FindSegmentSample
 from edgeimpulse_api.models.find_segment_sample_response import FindSegmentSampleResponse
 from edgeimpulse_api.models.find_segment_sample_response_all_of import FindSegmentSampleResponseAllOf
 from edgeimpulse_api.models.find_segment_sample_response_all_of_segments import FindSegmentSampleResponseAllOfSegments
+from edgeimpulse_api.models.fold_model_metadata import FoldModelMetadata
+from edgeimpulse_api.models.fold_model_metadata_all_of import FoldModelMetadataAllOf
 from edgeimpulse_api.models.generate_features_request import GenerateFeaturesRequest
 from edgeimpulse_api.models.generate_post_processing_features_for_sample200_response import GeneratePostProcessingFeaturesForSample200Response
 from edgeimpulse_api.models.generic_api_response import GenericApiResponse
@@ -568,6 +570,8 @@ from edgeimpulse_api.models.job_status import JobStatus
 from edgeimpulse_api.models.job_summary_response import JobSummaryResponse
 from edgeimpulse_api.models.job_summary_response_all_of import JobSummaryResponseAllOf
 from edgeimpulse_api.models.job_summary_response_all_of_summary import JobSummaryResponseAllOfSummary
+from edgeimpulse_api.models.k_folds_metadata import KFoldsMetadata
+from edgeimpulse_api.models.k_folds_validation_config import KFoldsValidationConfig
 from edgeimpulse_api.models.keep_device_debug_stream_alive_request import KeepDeviceDebugStreamAliveRequest
 from edgeimpulse_api.models.keras_config import KerasConfig
 from edgeimpulse_api.models.keras_custom_metric import KerasCustomMetric
@@ -575,6 +579,8 @@ from edgeimpulse_api.models.keras_model_layer import KerasModelLayer
 from edgeimpulse_api.models.keras_model_layer_input import KerasModelLayerInput
 from edgeimpulse_api.models.keras_model_layer_output import KerasModelLayerOutput
 from edgeimpulse_api.models.keras_model_metadata import KerasModelMetadata
+from edgeimpulse_api.models.keras_model_metadata_all_of import KerasModelMetadataAllOf
+from edgeimpulse_api.models.keras_model_metadata_base import KerasModelMetadataBase
 from edgeimpulse_api.models.keras_model_metadata_graph import KerasModelMetadataGraph
 from edgeimpulse_api.models.keras_model_metadata_graph_series import KerasModelMetadataGraphSeries
 from edgeimpulse_api.models.keras_model_metadata_metrics import KerasModelMetadataMetrics
@@ -797,6 +803,7 @@ from edgeimpulse_api.models.portal_file import PortalFile
 from edgeimpulse_api.models.portal_info_response import PortalInfoResponse
 from edgeimpulse_api.models.portal_info_response_all_of import PortalInfoResponseAllOf
 from edgeimpulse_api.models.post_processing_block import PostProcessingBlock
+from edgeimpulse_api.models.post_processing_block_type import PostProcessingBlockType
 from edgeimpulse_api.models.post_processing_config import PostProcessingConfig
 from edgeimpulse_api.models.post_processing_config_request import PostProcessingConfigRequest
 from edgeimpulse_api.models.post_processing_config_response import PostProcessingConfigResponse

{edgeimpulse_api-1.96.2 → edgeimpulse_api-1.96.3}/edgeimpulse_api/models/__init__.py

@@ -349,6 +349,8 @@ from edgeimpulse_api.models.find_segment_sample_request import FindSegmentSample
 from edgeimpulse_api.models.find_segment_sample_response import FindSegmentSampleResponse
 from edgeimpulse_api.models.find_segment_sample_response_all_of import FindSegmentSampleResponseAllOf
 from edgeimpulse_api.models.find_segment_sample_response_all_of_segments import FindSegmentSampleResponseAllOfSegments
+from edgeimpulse_api.models.fold_model_metadata import FoldModelMetadata
+from edgeimpulse_api.models.fold_model_metadata_all_of import FoldModelMetadataAllOf
 from edgeimpulse_api.models.generate_features_request import GenerateFeaturesRequest
 from edgeimpulse_api.models.generate_post_processing_features_for_sample200_response import GeneratePostProcessingFeaturesForSample200Response
 from edgeimpulse_api.models.generic_api_response import GenericApiResponse
@@ -527,6 +529,8 @@ from edgeimpulse_api.models.job_status import JobStatus
 from edgeimpulse_api.models.job_summary_response import JobSummaryResponse
 from edgeimpulse_api.models.job_summary_response_all_of import JobSummaryResponseAllOf
 from edgeimpulse_api.models.job_summary_response_all_of_summary import JobSummaryResponseAllOfSummary
+from edgeimpulse_api.models.k_folds_metadata import KFoldsMetadata
+from edgeimpulse_api.models.k_folds_validation_config import KFoldsValidationConfig
 from edgeimpulse_api.models.keep_device_debug_stream_alive_request import KeepDeviceDebugStreamAliveRequest
 from edgeimpulse_api.models.keras_config import KerasConfig
 from edgeimpulse_api.models.keras_custom_metric import KerasCustomMetric
@@ -534,6 +538,8 @@ from edgeimpulse_api.models.keras_model_layer import KerasModelLayer
 from edgeimpulse_api.models.keras_model_layer_input import KerasModelLayerInput
 from edgeimpulse_api.models.keras_model_layer_output import KerasModelLayerOutput
 from edgeimpulse_api.models.keras_model_metadata import KerasModelMetadata
+from edgeimpulse_api.models.keras_model_metadata_all_of import KerasModelMetadataAllOf
+from edgeimpulse_api.models.keras_model_metadata_base import KerasModelMetadataBase
 from edgeimpulse_api.models.keras_model_metadata_graph import KerasModelMetadataGraph
 from edgeimpulse_api.models.keras_model_metadata_graph_series import KerasModelMetadataGraphSeries
 from edgeimpulse_api.models.keras_model_metadata_metrics import KerasModelMetadataMetrics
@@ -756,6 +762,7 @@ from edgeimpulse_api.models.portal_file import PortalFile
 from edgeimpulse_api.models.portal_info_response import PortalInfoResponse
 from edgeimpulse_api.models.portal_info_response_all_of import PortalInfoResponseAllOf
 from edgeimpulse_api.models.post_processing_block import PostProcessingBlock
+from edgeimpulse_api.models.post_processing_block_type import PostProcessingBlockType
 from edgeimpulse_api.models.post_processing_config import PostProcessingConfig
 from edgeimpulse_api.models.post_processing_config_request import PostProcessingConfigRequest
 from edgeimpulse_api.models.post_processing_config_response import PostProcessingConfigResponse

edgeimpulse_api-1.96.3/edgeimpulse_api/models/fold_model_metadata.py

@@ -0,0 +1,129 @@
+# coding: utf-8
+
+"""
+    Edge Impulse API
+
+    No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator)  # noqa: E501
+
+    The version of the OpenAPI document: 1.0.0
+    Generated by: https://openapi-generator.tech
+"""
+
+
+from __future__ import annotations
+from inspect import getfullargspec
+import pprint
+import re  # noqa: F401
+import json
+
+from datetime import datetime
+from typing import List, Optional
+from pydantic.v1 import BaseModel, Field, StrictBool, StrictStr, conint
+from edgeimpulse_api.models.block_threshold import BlockThreshold
+from edgeimpulse_api.models.image_input_scaling import ImageInputScaling
+from edgeimpulse_api.models.keras_model_layer import KerasModelLayer
+from edgeimpulse_api.models.keras_model_metadata_graph import KerasModelMetadataGraph
+from edgeimpulse_api.models.keras_model_metadata_metrics import KerasModelMetadataMetrics
+from edgeimpulse_api.models.keras_model_mode import KerasModelMode
+from edgeimpulse_api.models.keras_model_type_enum import KerasModelTypeEnum
+from edgeimpulse_api.models.object_detection_last_layer import ObjectDetectionLastLayer
+
+class FoldModelMetadata(BaseModel):
+    created: datetime = Field(..., description="Date when the model was trained")
+    layers: List[KerasModelLayer] = Field(..., description="Layers of the neural network")
+    class_names: List[StrictStr] = Field(..., alias="classNames", description="Labels for the output layer")
+    labels: List[StrictStr] = Field(..., description="Original labels in the dataset when features were generated, e.g. used to render the feature explorer.")
+    available_model_types: List[KerasModelTypeEnum] = Field(..., alias="availableModelTypes", description="The types of model that are available")
+    recommended_model_type: KerasModelTypeEnum = Field(..., alias="recommendedModelType")
+    model_validation_metrics: List[KerasModelMetadataMetrics] = Field(..., alias="modelValidationMetrics", description="Metrics for each of the available model types")
+    has_trained_model: StrictBool = Field(..., alias="hasTrainedModel")
+    mode: KerasModelMode = ...
+    object_detection_last_layer: Optional[ObjectDetectionLastLayer] = Field(None, alias="objectDetectionLastLayer")
+    image_input_scaling: ImageInputScaling = Field(..., alias="imageInputScaling")
+    thresholds: List[BlockThreshold] = Field(..., description="List of configurable thresholds for this block.")
+    tensorboard_graphs: Optional[List[KerasModelMetadataGraph]] = Field(None, alias="tensorboardGraphs")
+    fold_id: conint(strict=True, ge=0) = Field(..., alias="foldId", description="A zero-indexed fold identifier")
+    fold_name: StrictStr = Field(..., alias="foldName", description="A one-indexed human-frendly fold name")
+    __properties = ["created", "layers", "classNames", "labels", "availableModelTypes", "recommendedModelType", "modelValidationMetrics", "hasTrainedModel", "mode", "objectDetectionLastLayer", "imageInputScaling", "thresholds", "tensorboardGraphs", "foldId", "foldName"]
+
+    class Config:
+        allow_population_by_field_name = True
+        validate_assignment = False
+
+    def to_str(self) -> str:
+        """Returns the string representation of the model using alias"""
+        return pprint.pformat(self.dict(by_alias=True))
+
+    def to_json(self,indent=None) -> str:
+        """Returns the JSON representation of the model using alias"""
+        return json.dumps(self.to_dict(),indent=indent)
+
+    @classmethod
+    def from_json(cls, json_str: str) -> FoldModelMetadata:
+        """Create an instance of FoldModelMetadata from a JSON string"""
+        return cls.from_dict(json.loads(json_str))
+
+    def to_dict(self):
+        """Returns the dictionary representation of the model using alias"""
+        _dict = self.dict(by_alias=True,
+                          exclude={
+                          },
+                          exclude_none=True)
+        # override the default output from pydantic by calling `to_dict()` of each item in layers (list)
+        _items = []
+        if self.layers:
+            for _item in self.layers:
+                if _item:
+                    _items.append(_item.to_dict())
+            _dict['layers'] = _items
+        # override the default output from pydantic by calling `to_dict()` of each item in model_validation_metrics (list)
+        _items = []
+        if self.model_validation_metrics:
+            for _item in self.model_validation_metrics:
+                if _item:
+                    _items.append(_item.to_dict())
+            _dict['modelValidationMetrics'] = _items
+        # override the default output from pydantic by calling `to_dict()` of each item in thresholds (list)
+        _items = []
+        if self.thresholds:
+            for _item in self.thresholds:
+                if _item:
+                    _items.append(_item.to_dict())
+            _dict['thresholds'] = _items
+        # override the default output from pydantic by calling `to_dict()` of each item in tensorboard_graphs (list)
+        _items = []
+        if self.tensorboard_graphs:
+            for _item in self.tensorboard_graphs:
+                if _item:
+                    _items.append(_item.to_dict())
+            _dict['tensorboardGraphs'] = _items
+        return _dict
+
+    @classmethod
+    def from_dict(cls, obj: dict) -> FoldModelMetadata:
+        """Create an instance of FoldModelMetadata from a dict"""
+        if obj is None:
+            return None
+
+        if type(obj) is not dict:
+            return FoldModelMetadata.construct(**obj)
+
+        _obj = FoldModelMetadata.construct(**{
+            "created": obj.get("created"),
+            "layers": [KerasModelLayer.from_dict(_item) for _item in obj.get("layers")] if obj.get("layers") is not None else None,
+            "class_names": obj.get("classNames"),
+            "labels": obj.get("labels"),
+            "available_model_types": obj.get("availableModelTypes"),
+            "recommended_model_type": obj.get("recommendedModelType"),
+            "model_validation_metrics": [KerasModelMetadataMetrics.from_dict(_item) for _item in obj.get("modelValidationMetrics")] if obj.get("modelValidationMetrics") is not None else None,
+            "has_trained_model": obj.get("hasTrainedModel"),
+            "mode": obj.get("mode"),
+            "object_detection_last_layer": obj.get("objectDetectionLastLayer"),
+            "image_input_scaling": obj.get("imageInputScaling"),
+            "thresholds": [BlockThreshold.from_dict(_item) for _item in obj.get("thresholds")] if obj.get("thresholds") is not None else None,
+            "tensorboard_graphs": [KerasModelMetadataGraph.from_dict(_item) for _item in obj.get("tensorboardGraphs")] if obj.get("tensorboardGraphs") is not None else None,
+            "fold_id": obj.get("foldId"),
+            "fold_name": obj.get("foldName")
+        })
+        return _obj
+

edgeimpulse_api-1.96.3/edgeimpulse_api/models/fold_model_metadata_all_of.py

@@ -0,0 +1,67 @@
+# coding: utf-8
+
+"""
+    Edge Impulse API
+
+    No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator)  # noqa: E501
+
+    The version of the OpenAPI document: 1.0.0
+    Generated by: https://openapi-generator.tech
+"""
+
+
+from __future__ import annotations
+from inspect import getfullargspec
+import pprint
+import re  # noqa: F401
+import json
+
+
+
+from pydantic.v1 import BaseModel, Field, StrictStr, conint
+
+class FoldModelMetadataAllOf(BaseModel):
+    fold_id: conint(strict=True, ge=0) = Field(..., alias="foldId", description="A zero-indexed fold identifier")
+    fold_name: StrictStr = Field(..., alias="foldName", description="A one-indexed human-frendly fold name")
+    __properties = ["foldId", "foldName"]
+
+    class Config:
+        allow_population_by_field_name = True
+        validate_assignment = False
+
+    def to_str(self) -> str:
+        """Returns the string representation of the model using alias"""
+        return pprint.pformat(self.dict(by_alias=True))
+
+    def to_json(self,indent=None) -> str:
+        """Returns the JSON representation of the model using alias"""
+        return json.dumps(self.to_dict(),indent=indent)
+
+    @classmethod
+    def from_json(cls, json_str: str) -> FoldModelMetadataAllOf:
+        """Create an instance of FoldModelMetadataAllOf from a JSON string"""
+        return cls.from_dict(json.loads(json_str))
+
+    def to_dict(self):
+        """Returns the dictionary representation of the model using alias"""
+        _dict = self.dict(by_alias=True,
+                          exclude={
+                          },
+                          exclude_none=True)
+        return _dict
+
+    @classmethod
+    def from_dict(cls, obj: dict) -> FoldModelMetadataAllOf:
+        """Create an instance of FoldModelMetadataAllOf from a dict"""
+        if obj is None:
+            return None
+
+        if type(obj) is not dict:
+            return FoldModelMetadataAllOf.construct(**obj)
+
+        _obj = FoldModelMetadataAllOf.construct(**{
+            "fold_id": obj.get("foldId"),
+            "fold_name": obj.get("foldName")
+        })
+        return _obj
+

{edgeimpulse_api-1.96.2 → edgeimpulse_api-1.96.3}/edgeimpulse_api/models/impulse_post_processing_block.py

@@ -19,10 +19,11 @@ import json
 from datetime import datetime
 from typing import Optional
 from pydantic.v1 import BaseModel, Field, StrictInt, StrictStr, conint
+from edgeimpulse_api.models.post_processing_block_type import PostProcessingBlockType
 
 class ImpulsePostProcessingBlock(BaseModel):
     id: conint(strict=True, ge=1) = Field(..., description="Identifier for this block. Make sure to up this number when creating a new block via `getNewBlockId`, and don't re-use identifiers. If the block hasn't changed, keep the ID as-is. ID must be unique across the project and greather than zero (>0).")
-    type: StrictStr = Field(..., description="Block type")
+    type: PostProcessingBlockType = ...
     name: StrictStr = Field(..., description="Block name, will be used in menus")
     title: StrictStr = Field(..., description="Block title, used in the impulse UI")
     created_by: Optional[StrictStr] = Field(None, alias="createdBy", description="The system component that created the block version (createImpulse | clone | tuner). Cannot be set via API.")

edgeimpulse_api-1.96.3/edgeimpulse_api/models/k_folds_metadata.py

@@ -0,0 +1,82 @@
+# coding: utf-8
+
+"""
+    Edge Impulse API
+
+    No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator)  # noqa: E501
+
+    The version of the OpenAPI document: 1.0.0
+    Generated by: https://openapi-generator.tech
+"""
+
+
+from __future__ import annotations
+from inspect import getfullargspec
+import pprint
+import re  # noqa: F401
+import json
+
+
+from typing import List, Optional
+from pydantic.v1 import BaseModel, Field, StrictBool, StrictInt, StrictStr
+from edgeimpulse_api.models.fold_model_metadata import FoldModelMetadata
+from edgeimpulse_api.models.keras_model_type_enum import KerasModelTypeEnum
+
+class KFoldsMetadata(BaseModel):
+    folds: List[FoldModelMetadata] = ...
+    has_final_run: Optional[StrictBool] = Field(None, alias="hasFinalRun", description="Set to true when the k-fold run includes a final-pass on all training data.")
+    persisted_fold_id: StrictInt = Field(..., alias="persistedFoldId", description="A zero-indexed identifier for the selected downstream fold (set to -1 if final run)")
+    persisted_fold_name: StrictStr = Field(..., alias="persistedFoldName", description="A one-indexed human-friendly fold name of the selected downstream fold")
+    persisted_fold_metric_type: Optional[KerasModelTypeEnum] = Field(None, alias="persistedFoldMetricType")
+    __properties = ["folds", "hasFinalRun", "persistedFoldId", "persistedFoldName", "persistedFoldMetricType"]
+
+    class Config:
+        allow_population_by_field_name = True
+        validate_assignment = False
+
+    def to_str(self) -> str:
+        """Returns the string representation of the model using alias"""
+        return pprint.pformat(self.dict(by_alias=True))
+
+    def to_json(self,indent=None) -> str:
+        """Returns the JSON representation of the model using alias"""
+        return json.dumps(self.to_dict(),indent=indent)
+
+    @classmethod
+    def from_json(cls, json_str: str) -> KFoldsMetadata:
+        """Create an instance of KFoldsMetadata from a JSON string"""
+        return cls.from_dict(json.loads(json_str))
+
+    def to_dict(self):
+        """Returns the dictionary representation of the model using alias"""
+        _dict = self.dict(by_alias=True,
+                          exclude={
+                          },
+                          exclude_none=True)
+        # override the default output from pydantic by calling `to_dict()` of each item in folds (list)
+        _items = []
+        if self.folds:
+            for _item in self.folds:
+                if _item:
+                    _items.append(_item.to_dict())
+            _dict['folds'] = _items
+        return _dict
+
+    @classmethod
+    def from_dict(cls, obj: dict) -> KFoldsMetadata:
+        """Create an instance of KFoldsMetadata from a dict"""
+        if obj is None:
+            return None
+
+        if type(obj) is not dict:
+            return KFoldsMetadata.construct(**obj)
+
+        _obj = KFoldsMetadata.construct(**{
+            "folds": [FoldModelMetadata.from_dict(_item) for _item in obj.get("folds")] if obj.get("folds") is not None else None,
+            "has_final_run": obj.get("hasFinalRun"),
+            "persisted_fold_id": obj.get("persistedFoldId"),
+            "persisted_fold_name": obj.get("persistedFoldName"),
+            "persisted_fold_metric_type": obj.get("persistedFoldMetricType")
+        })
+        return _obj
+

edgeimpulse_api-1.96.3/edgeimpulse_api/models/k_folds_validation_config.py

@@ -0,0 +1,69 @@
+# coding: utf-8
+
+"""
+    Edge Impulse API
+
+    No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator)  # noqa: E501
+
+    The version of the OpenAPI document: 1.0.0
+    Generated by: https://openapi-generator.tech
+"""
+
+
+from __future__ import annotations
+from inspect import getfullargspec
+import pprint
+import re  # noqa: F401
+import json
+
+
+from typing import Optional
+from pydantic.v1 import BaseModel, Field, StrictBool
+
+class KFoldsValidationConfig(BaseModel):
+    num_folds: float = Field(..., alias="numFolds", description="Number of \"k\" folds")
+    include_final_training_run: Optional[StrictBool] = Field(None, alias="includeFinalTrainingRun", description="Optional flag for activating the final training run, performed on the entire training dataset after the k fold runs complete (defaults to off).")
+    extra_epochs: Optional[float] = Field(None, alias="extraEpochs", description="Number of additional training epochs. The final model will be trained on the median epoch count from the previous k runs + extraEpochs. ")
+    __properties = ["numFolds", "includeFinalTrainingRun", "extraEpochs"]
+
+    class Config:
+        allow_population_by_field_name = True
+        validate_assignment = False
+
+    def to_str(self) -> str:
+        """Returns the string representation of the model using alias"""
+        return pprint.pformat(self.dict(by_alias=True))
+
+    def to_json(self,indent=None) -> str:
+        """Returns the JSON representation of the model using alias"""
+        return json.dumps(self.to_dict(),indent=indent)
+
+    @classmethod
+    def from_json(cls, json_str: str) -> KFoldsValidationConfig:
+        """Create an instance of KFoldsValidationConfig from a JSON string"""
+        return cls.from_dict(json.loads(json_str))
+
+    def to_dict(self):
+        """Returns the dictionary representation of the model using alias"""
+        _dict = self.dict(by_alias=True,
+                          exclude={
+                          },
+                          exclude_none=True)
+        return _dict
+
+    @classmethod
+    def from_dict(cls, obj: dict) -> KFoldsValidationConfig:
+        """Create an instance of KFoldsValidationConfig from a dict"""
+        if obj is None:
+            return None
+
+        if type(obj) is not dict:
+            return KFoldsValidationConfig.construct(**obj)
+
+        _obj = KFoldsValidationConfig.construct(**{
+            "num_folds": obj.get("numFolds"),
+            "include_final_training_run": obj.get("includeFinalTrainingRun"),
+            "extra_epochs": obj.get("extraEpochs")
+        })
+        return _obj
+

{edgeimpulse_api-1.96.2 → edgeimpulse_api-1.96.3}/edgeimpulse_api/models/keras_config.py

@@ -26,6 +26,7 @@ from edgeimpulse_api.models.augmentation_policy_spectrogram import AugmentationP
 from edgeimpulse_api.models.block_parameters import BlockParameters
 from edgeimpulse_api.models.block_threshold import BlockThreshold
 from edgeimpulse_api.models.dependency_data import DependencyData
+from edgeimpulse_api.models.k_folds_validation_config import KFoldsValidationConfig
 from edgeimpulse_api.models.keras_model_type_enum import KerasModelTypeEnum
 from edgeimpulse_api.models.keras_model_variant_enum import KerasModelVariantEnum
 from edgeimpulse_api.models.keras_visual_layer import KerasVisualLayer
@@ -64,8 +65,9 @@ class KerasConfig(BaseModel):
     last_shown_model_variant: Optional[KerasModelVariantEnum] = Field(None, alias="lastShownModelVariant")
     block_parameters: Optional[BlockParameters] = Field(None, alias="blockParameters")
     thresholds: List[BlockThreshold] = Field(..., description="List of configurable thresholds for this block.")
+    k_folds_validation_config: Optional[KFoldsValidationConfig] = Field(None, alias="kFoldsValidationConfig")
     is_multi_head: Optional[StrictBool] = Field(None, alias="isMultiHead", description="Whether this model is configured for multi-head outputs.")
-    __properties = ["dependencies", "trained", "name", "type", "script", "minimumConfidenceRating", "selectedModelType", "mode", "visualLayers", "trainingCycles", "learningRate", "batchSize", "defaultBatchSize", "shape", "trainTestSplit", "autoClassWeights", "useLearnedOptimizer", "augmentationPolicyImage", "augmentationPolicySpectrogram", "transferLearningModels", "profileInt8", "skipEmbeddingsAndMemory", "akidaEdgeLearningConfig", "customValidationMetadataKey", "showAdvancedTrainingSettings", "showAugmentationTrainingSettings", "customParameters", "anomalyCapacity", "lastShownModelVariant", "blockParameters", "thresholds", "isMultiHead"]
+    __properties = ["dependencies", "trained", "name", "type", "script", "minimumConfidenceRating", "selectedModelType", "mode", "visualLayers", "trainingCycles", "learningRate", "batchSize", "defaultBatchSize", "shape", "trainTestSplit", "autoClassWeights", "useLearnedOptimizer", "augmentationPolicyImage", "augmentationPolicySpectrogram", "transferLearningModels", "profileInt8", "skipEmbeddingsAndMemory", "akidaEdgeLearningConfig", "customValidationMetadataKey", "showAdvancedTrainingSettings", "showAugmentationTrainingSettings", "customParameters", "anomalyCapacity", "lastShownModelVariant", "blockParameters", "thresholds", "kFoldsValidationConfig", "isMultiHead"]
 
     @validator('mode')
     def mode_validate_enum(cls, v):
@@ -129,6 +131,9 @@ class KerasConfig(BaseModel):
                 if _item:
                     _items.append(_item.to_dict())
             _dict['thresholds'] = _items
+        # override the default output from pydantic by calling `to_dict()` of k_folds_validation_config
+        if self.k_folds_validation_config:
+            _dict['kFoldsValidationConfig'] = self.k_folds_validation_config.to_dict()
         return _dict
 
     @classmethod
@@ -172,6 +177,7 @@ class KerasConfig(BaseModel):
             "last_shown_model_variant": obj.get("lastShownModelVariant"),
             "block_parameters": BlockParameters.from_dict(obj.get("blockParameters")) if obj.get("blockParameters") is not None else None,
             "thresholds": [BlockThreshold.from_dict(_item) for _item in obj.get("thresholds")] if obj.get("thresholds") is not None else None,
+            "k_folds_validation_config": KFoldsValidationConfig.from_dict(obj.get("kFoldsValidationConfig")) if obj.get("kFoldsValidationConfig") is not None else None,
             "is_multi_head": obj.get("isMultiHead")
         })
         return _obj

edgeimpulse_api-1.96.3/edgeimpulse_api/models/keras_model_metadata.py

@@ -0,0 +1,131 @@
+# coding: utf-8
+
+"""
+    Edge Impulse API
+
+    No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator)  # noqa: E501
+
+    The version of the OpenAPI document: 1.0.0
+    Generated by: https://openapi-generator.tech
+"""
+
+
+from __future__ import annotations
+from inspect import getfullargspec
+import pprint
+import re  # noqa: F401
+import json
+
+from datetime import datetime
+from typing import List, Optional
+from pydantic.v1 import BaseModel, Field, StrictBool, StrictStr
+from edgeimpulse_api.models.block_threshold import BlockThreshold
+from edgeimpulse_api.models.image_input_scaling import ImageInputScaling
+from edgeimpulse_api.models.k_folds_metadata import KFoldsMetadata
+from edgeimpulse_api.models.keras_model_layer import KerasModelLayer
+from edgeimpulse_api.models.keras_model_metadata_graph import KerasModelMetadataGraph
+from edgeimpulse_api.models.keras_model_metadata_metrics import KerasModelMetadataMetrics
+from edgeimpulse_api.models.keras_model_mode import KerasModelMode
+from edgeimpulse_api.models.keras_model_type_enum import KerasModelTypeEnum
+from edgeimpulse_api.models.object_detection_last_layer import ObjectDetectionLastLayer
+
+class KerasModelMetadata(BaseModel):
+    created: datetime = Field(..., description="Date when the model was trained")
+    layers: List[KerasModelLayer] = Field(..., description="Layers of the neural network")
+    class_names: List[StrictStr] = Field(..., alias="classNames", description="Labels for the output layer")
+    labels: List[StrictStr] = Field(..., description="Original labels in the dataset when features were generated, e.g. used to render the feature explorer.")
+    available_model_types: List[KerasModelTypeEnum] = Field(..., alias="availableModelTypes", description="The types of model that are available")
+    recommended_model_type: KerasModelTypeEnum = Field(..., alias="recommendedModelType")
+    model_validation_metrics: List[KerasModelMetadataMetrics] = Field(..., alias="modelValidationMetrics", description="Metrics for each of the available model types")
+    has_trained_model: StrictBool = Field(..., alias="hasTrainedModel")
+    mode: KerasModelMode = ...
+    object_detection_last_layer: Optional[ObjectDetectionLastLayer] = Field(None, alias="objectDetectionLastLayer")
+    image_input_scaling: ImageInputScaling = Field(..., alias="imageInputScaling")
+    thresholds: List[BlockThreshold] = Field(..., description="List of configurable thresholds for this block.")
+    tensorboard_graphs: Optional[List[KerasModelMetadataGraph]] = Field(None, alias="tensorboardGraphs")
+    k_folds_metadata: Optional[KFoldsMetadata] = Field(None, alias="kFoldsMetadata")
+    __properties = ["created", "layers", "classNames", "labels", "availableModelTypes", "recommendedModelType", "modelValidationMetrics", "hasTrainedModel", "mode", "objectDetectionLastLayer", "imageInputScaling", "thresholds", "tensorboardGraphs", "kFoldsMetadata"]
+
+    class Config:
+        allow_population_by_field_name = True
+        validate_assignment = False
+
+    def to_str(self) -> str:
+        """Returns the string representation of the model using alias"""
+        return pprint.pformat(self.dict(by_alias=True))
+
+    def to_json(self,indent=None) -> str:
+        """Returns the JSON representation of the model using alias"""
+        return json.dumps(self.to_dict(),indent=indent)
+
+    @classmethod
+    def from_json(cls, json_str: str) -> KerasModelMetadata:
+        """Create an instance of KerasModelMetadata from a JSON string"""
+        return cls.from_dict(json.loads(json_str))
+
+    def to_dict(self):
+        """Returns the dictionary representation of the model using alias"""
+        _dict = self.dict(by_alias=True,
+                          exclude={
+                          },
+                          exclude_none=True)
+        # override the default output from pydantic by calling `to_dict()` of each item in layers (list)
+        _items = []
+        if self.layers:
+            for _item in self.layers:
+                if _item:
+                    _items.append(_item.to_dict())
+            _dict['layers'] = _items
+        # override the default output from pydantic by calling `to_dict()` of each item in model_validation_metrics (list)
+        _items = []
+        if self.model_validation_metrics:
+            for _item in self.model_validation_metrics:
+                if _item:
+                    _items.append(_item.to_dict())
+            _dict['modelValidationMetrics'] = _items
+        # override the default output from pydantic by calling `to_dict()` of each item in thresholds (list)
+        _items = []
+        if self.thresholds:
+            for _item in self.thresholds:
+                if _item:
+                    _items.append(_item.to_dict())
+            _dict['thresholds'] = _items
+        # override the default output from pydantic by calling `to_dict()` of each item in tensorboard_graphs (list)
+        _items = []
+        if self.tensorboard_graphs:
+            for _item in self.tensorboard_graphs:
+                if _item:
+                    _items.append(_item.to_dict())
+            _dict['tensorboardGraphs'] = _items
+        # override the default output from pydantic by calling `to_dict()` of k_folds_metadata
+        if self.k_folds_metadata:
+            _dict['kFoldsMetadata'] = self.k_folds_metadata.to_dict()
+        return _dict
+
+    @classmethod
+    def from_dict(cls, obj: dict) -> KerasModelMetadata:
+        """Create an instance of KerasModelMetadata from a dict"""
+        if obj is None:
+            return None
+
+        if type(obj) is not dict:
+            return KerasModelMetadata.construct(**obj)
+
+        _obj = KerasModelMetadata.construct(**{
+            "created": obj.get("created"),
+            "layers": [KerasModelLayer.from_dict(_item) for _item in obj.get("layers")] if obj.get("layers") is not None else None,
+            "class_names": obj.get("classNames"),
+            "labels": obj.get("labels"),
+            "available_model_types": obj.get("availableModelTypes"),
+            "recommended_model_type": obj.get("recommendedModelType"),
+            "model_validation_metrics": [KerasModelMetadataMetrics.from_dict(_item) for _item in obj.get("modelValidationMetrics")] if obj.get("modelValidationMetrics") is not None else None,
+            "has_trained_model": obj.get("hasTrainedModel"),
+            "mode": obj.get("mode"),
+            "object_detection_last_layer": obj.get("objectDetectionLastLayer"),
+            "image_input_scaling": obj.get("imageInputScaling"),
+            "thresholds": [BlockThreshold.from_dict(_item) for _item in obj.get("thresholds")] if obj.get("thresholds") is not None else None,
+            "tensorboard_graphs": [KerasModelMetadataGraph.from_dict(_item) for _item in obj.get("tensorboardGraphs")] if obj.get("tensorboardGraphs") is not None else None,
+            "k_folds_metadata": KFoldsMetadata.from_dict(obj.get("kFoldsMetadata")) if obj.get("kFoldsMetadata") is not None else None
+        })
+        return _obj
+