Shortcuts

KeypointDetectionData

class flash.image.keypoint_detection.data.KeypointDetectionData(train_input=None, val_input=None, test_input=None, predict_input=None, data_fetcher=None, val_split=None, batch_size=None, num_workers=0, sampler=None, pin_memory=True, persistent_workers=True, output_transform=None)[source]
classmethod from_coco(train_folder=None, train_ann_file=None, val_folder=None, val_ann_file=None, test_folder=None, test_ann_file=None, predict_folder=None, train_transform=<class 'flash.core.integrations.icevision.transforms.IceVisionInputTransform'>, val_transform=<class 'flash.core.integrations.icevision.transforms.IceVisionInputTransform'>, test_transform=<class 'flash.core.integrations.icevision.transforms.IceVisionInputTransform'>, predict_transform=<class 'flash.core.integrations.icevision.transforms.IceVisionInputTransform'>, parser=<class 'object'>, input_cls=<class 'flash.core.integrations.icevision.data.IceVisionInput'>, transform_kwargs=None, **data_module_kwargs)[source]

Creates a KeypointDetectionData object from the given data folders and annotation files in the COCO format.

Parameters
  • train_folder (Optional[str]) – The folder containing the train data.

  • train_ann_file (Optional[str]) – The COCO format annotation file.

  • val_folder (Optional[str]) – The folder containing the validation data.

  • val_ann_file (Optional[str]) – The COCO format annotation file.

  • test_folder (Optional[str]) – The folder containing the test data.

  • test_ann_file (Optional[str]) – The COCO format annotation file.

  • predict_folder (Optional[str]) – The folder containing the predict data.

  • train_transform (~INPUT_TRANSFORM_TYPE) – The dictionary of transforms to use during training which maps InputTransform hook names to callable transforms.

  • val_transform (~INPUT_TRANSFORM_TYPE) – The dictionary of transforms to use during validation which maps InputTransform hook names to callable transforms.

  • test_transform (~INPUT_TRANSFORM_TYPE) – The dictionary of transforms to use during testing which maps InputTransform hook names to callable transforms.

  • predict_transform (~INPUT_TRANSFORM_TYPE) – The dictionary of transforms to use during predicting which maps InputTransform hook names to callable transforms.

  • input_cls (Type[Input]) – The Input used to create the dataset.

  • transform_kwargs (Optional[Dict]) – Keyword arguments provided to the transform on instantiation.

  • data_module_kwargs (Any) – Keyword arguments provided to the DataModule on instantiation.

classmethod from_files(predict_files=None, predict_transform=<class 'flash.core.integrations.icevision.transforms.IceVisionInputTransform'>, input_cls=<class 'flash.core.integrations.icevision.data.IceVisionInput'>, transform_kwargs=None, **data_module_kwargs)[source]

Creates a DataModule object from the given a list of files.

This is supported only for the predicting stage.

Parameters
  • predict_files (Optional[List[str]]) – The list of files containing the predict data.

  • predict_transform (~INPUT_TRANSFORM_TYPE) – The dictionary of transforms to use during predicting which maps.

  • input_cls (Type[Input]) – The Input used to create the dataset.

  • transform_kwargs (Optional[Dict]) – Keyword arguments provided to the transform on instantiation.

  • data_module_kwargs (Any) – The keywords arguments for creating the datamodule.

Return type

DataModule

Returns

The constructed data module.

classmethod from_folders(predict_folder=None, predict_transform=<class 'flash.core.integrations.icevision.transforms.IceVisionInputTransform'>, input_cls=<class 'flash.core.integrations.icevision.data.IceVisionInput'>, transform_kwargs=None, **data_module_kwargs)[source]

Creates a DataModule object from the given folders.

This is supported only for the predicting stage.

Parameters
  • predict_folder (Optional[str]) – The folder containing the predict data.

  • predict_transform (~INPUT_TRANSFORM_TYPE) – The dictionary of transforms to use during predicting which maps

  • input_cls (Type[Input]) – The Input used to create the dataset.

  • transform_kwargs (Optional[Dict]) – Keyword arguments provided to the transform on instantiation.

  • data_module_kwargs (Any) – The keywords arguments for creating the datamodule.

Return type

DataModule

Returns

The constructed data module.

input_transform_cls

alias of flash.core.integrations.icevision.transforms.IceVisionInputTransform

Read the Docs v: stable
Versions
latest
stable
0.6.0
0.5.2
0.5.1
0.5.0
0.4.0
0.3.2
0.3.1
0.3.0
0.2.3
0.2.2
0.2.1
0.2.0
0.1.0post1
docs-fix_typing
Downloads
pdf
html
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.