InstanceSegmentationData¶

class flash.image.instance_segmentation.data.InstanceSegmentationData(train_input=None, val_input=None, test_input=None, predict_input=None, data_fetcher=None, transform=<class 'flash.core.data.io.input_transform.InputTransform'>, transform_kwargs=None, val_split=None, batch_size=None, num_workers=0, sampler=None, pin_memory=True, persistent_workers=False)[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, input_cls=<class 'flash.core.integrations.icevision.data.IceVisionInput'>, transform=<class 'flash.core.integrations.icevision.transforms.IceVisionInputTransform'>, transform_kwargs=None, **data_module_kwargs)[source]¶

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

For help understanding and using the COCO format, take a look at this tutorial: Create COCO annotations from scratch.

To learn how to customize the transforms applied for each stage, read our customizing transforms guide.

Parameters

train_folder¶ (Optional[str]) – The folder containing images to use when training.
train_ann_file¶ (Optional[str]) – The COCO format annotation file to use when training.
val_folder¶ (Optional[str]) – The folder containing images to use when validating.
val_ann_file¶ (Optional[str]) – The COCO format annotation file to use when validating.
test_folder¶ (Optional[str]) – The folder containing images to use when testing.
test_ann_file¶ (Optional[str]) – The COCO format annotation file to use when testing.
predict_folder¶ (Optional[str]) – The folder containing images to use when predicting.
input_cls¶ (Type[Input]) – The Input type to use for loading the data.
transform¶ (TypeVar(INPUT_TRANSFORM_TYPE, Type[flash.core.data.io.input_transform.InputTransform], Callable, Tuple[Union[StrEnum, str], Dict[str, Any]], Union[StrEnum, str], None)) – The InputTransform type to use.
transform_kwargs¶ (Optional[Dict]) – Dict of keyword arguments to be provided when instantiating the transforms.
data_module_kwargs¶ (Any) – Additional keyword arguments to provide to the DataModule constructor.

Returns

The constructed InstanceSegmentationData.

Examples

The folder train_folder has the following contents:

train_folder
├── image_1.png
├── image_2.png
├── image_3.png
...

The file train_annotations.json contains the following:

{
    "annotations": [
        {"area": 50, "bbox": [10, 20, 5, 10], "category_id": 1, "id": 1, "image_id": 1, "iscrowd": 0,
        "segmentation": [[10, 20, 15, 20, 15, 30, 10, 30]]},
        {"area": 100, "bbox": [20, 30, 10, 10], "category_id": 2, "id": 2, "image_id": 2, "iscrowd": 0,
        "segmentation": [[20, 30, 30, 30, 30, 40, 20, 40]]},
        {"area": 125, "bbox": [10, 20, 5, 25], "category_id": 1, "id": 3, "image_id": 3, "iscrowd": 0,
        "segmentation": [[10, 20, 15, 20, 15, 45, 10, 45]]}
    ], "categories": [
        {"id": 1, "name": "cat", "supercategory": "annimal"},
        {"id": 2, "name": "dog", "supercategory": "annimal"}
    ], "images": [
        {"file_name": "image_1.png", "height": 64, "width": 64, "id": 1},
        {"file_name": "image_2.png", "height": 64, "width": 64, "id": 2},
        {"file_name": "image_3.png", "height": 64, "width": 64, "id": 3}
    ]
}

>>> from flash import Trainer
>>> from flash.image import InstanceSegmentation, InstanceSegmentationData
>>> datamodule = InstanceSegmentationData.from_coco(
...     train_folder="train_folder",
...     train_ann_file="train_annotations.json",
...     predict_folder="predict_folder",
...     transform_kwargs=dict(image_size=(128, 128)),
...     batch_size=2,
... )
>>> datamodule.num_classes
3
>>> datamodule.labels
['background', 'cat', 'dog']
>>> model = InstanceSegmentation(num_classes=datamodule.num_classes)
>>> trainer = Trainer(fast_dev_run=True)
>>> trainer.fit(model, datamodule=datamodule)  
Training...
>>> trainer.predict(model, datamodule=datamodule)  
Predicting...

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¶ (TypeVar(INPUT_TRANSFORM_TYPE, Type[flash.core.data.io.input_transform.InputTransform], Callable, Tuple[Union[StrEnum, str], Dict[str, Any]], Union[StrEnum, str], None)) – 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¶ (TypeVar(INPUT_TRANSFORM_TYPE, Type[flash.core.data.io.input_transform.InputTransform], Callable, Tuple[Union[StrEnum, str], Dict[str, Any]], Union[StrEnum, str], None)) – 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_voc(labels, train_folder=None, train_target_folder=None, train_ann_folder=None, val_folder=None, val_target_folder=None, val_ann_folder=None, test_folder=None, test_target_folder=None, test_ann_folder=None, predict_folder=None, input_cls=<class 'flash.core.integrations.icevision.data.IceVisionInput'>, transform=<class 'flash.core.integrations.icevision.transforms.IceVisionInputTransform'>, transform_kwargs=None, **data_module_kwargs)[source]¶

Creates a InstanceSegmentationData object from the given data folders, mask folders, and annotation files in the PASCAL VOC (Visual Object Challenge) XML format.

Note

All three arguments *_folder, *_target_folder, and *_ann_folder are needed to load data for a particular stage.

To learn how to customize the transforms applied for each stage, read our customizing transforms guide.

Parameters

labels¶ (List[str]) – A list of class labels. Note that the list should not include a label for the background class which will be added automatically as class zero (additional labels will be sorted).
train_folder¶ (Optional[str]) – The folder containing images to use when training.
train_target_folder¶ (Optional[str]) – The folder containing mask images to use when training.
train_ann_folder¶ (Optional[str]) – The folder containing VOC format annotation files to use when training.
val_folder¶ (Optional[str]) – The folder containing images to use when validating.
val_target_folder¶ (Optional[str]) – The folder containing mask images to use when validating.
val_ann_folder¶ (Optional[str]) – The folder containing VOC format annotation files to use when validating.
test_folder¶ (Optional[str]) – The folder containing images to use when testing.
test_target_folder¶ (Optional[str]) – The folder containing mask images to use when testing.
test_ann_folder¶ (Optional[str]) – The folder containing VOC format annotation files to use when testing.
predict_folder¶ (Optional[str]) – The folder containing images to use when predicting.
input_cls¶ (Type[Input]) – The Input type to use for loading the data.
transform¶ (TypeVar(INPUT_TRANSFORM_TYPE, Type[flash.core.data.io.input_transform.InputTransform], Callable, Tuple[Union[StrEnum, str], Dict[str, Any]], Union[StrEnum, str], None)) – The InputTransform type to use.
transform_kwargs¶ (Optional[Dict]) – Dict of keyword arguments to be provided when instantiating the transforms.
data_module_kwargs¶ (Any) – Additional keyword arguments to provide to the DataModule constructor.

Returns

The constructed InstanceSegmentationData.

Examples

The folder train_folder has the following contents:

train_folder
├── image_1.png
├── image_2.png
├── image_3.png
...

The folder train_masks has the following contents:

train_masks
├── image_1.png
├── image_2.png
├── image_3.png
...

The folder train_annotations has the following contents:

train_annotations
├── image_1.xml
├── image_2.xml
├── image_3.xml
...

The file image_1.xml contains the following:

<annotation>
    <filename>image_0.png</filename>
    <path>image_0.png</path>
    <source><database>example</database></source>
    <size><width>64</width><height>64</height><depth>3</depth></size>
    <object>
        <name>cat</name>
        <pose>Unspecified</pose>
        <truncated>0</truncated>
        <difficult>0</difficult>
        <occluded>0</occluded>
        <bndbox><xmin>10</xmin><xmax>15</xmax><ymin>20</ymin><ymax>30</ymax></bndbox>
    </object>
</annotation>

>>> from flash import Trainer
>>> from flash.image import InstanceSegmentation, InstanceSegmentationData
>>> datamodule = InstanceSegmentationData.from_voc(
...     ["cat", "dog"],
...     train_folder="train_folder",
...     train_target_folder="train_masks",
...     train_ann_folder="train_annotations",
...     predict_folder="predict_folder",
...     transform_kwargs=dict(image_size=(128, 128)),
...     batch_size=2,
... )
>>> datamodule.num_classes
3
>>> datamodule.labels
['background', 'cat', 'dog']
>>> model = InstanceSegmentation(num_classes=datamodule.num_classes)
>>> trainer = Trainer(fast_dev_run=True)
>>> trainer.fit(model, datamodule=datamodule)  
Training...
>>> trainer.predict(model, datamodule=datamodule)  
Predicting...

input_transform_cls¶: alias of flash.core.integrations.icevision.transforms.IceVisionInputTransform