Shortcuts

flash.image

Classification

ImageClassifier

The ImageClassifier is a Task for classifying images.

ImageClassificationFiftyOneInput

ImageClassificationData

Data module for image classification tasks.

ImageClassificationInputTransform

Preprocssing of data of image classification.

classification.data.MatplotlibVisualization

Process and show the image batch and its associated label using matplotlib.

classification.transforms.default_transforms

The default transforms for image classification: resize the image, convert the image and target to a tensor, collate the batch, and apply normalization.

classification.transforms.train_default_transforms

During training, we apply the default transforms with additional RandomHorizontalFlip.

Object Detection

ObjectDetector

The ObjectDetector is a Task for detecting objects in images.

ObjectDetectionData

detection.data.FiftyOneParser

detection.data.ObjectDetectionFiftyOneInput

detection.output.FiftyOneDetectionLabelsOutput

A Output which converts model outputs to FiftyOne detection format.

detection.data.ObjectDetectionInputTransform

Keypoint Detection

KeypointDetector

The KeypointDetector is a Task for detecting keypoints in images.

KeypointDetectionData

keypoint_detection.data.KeypointDetectionInputTransform

Instance Segmentation

InstanceSegmentation

The InstanceSegmentation is a Task for detecting objects in images.

InstanceSegmentationData

instance_segmentation.data.InstanceSegmentationInputTransform

Embedding

ImageEmbedder

The ImageEmbedder is a Task for obtaining feature vectors (embeddings) from images.

Segmentation

SemanticSegmentation

SemanticSegmentation is a Task for semantic segmentation of images.

SemanticSegmentationData

Data module for semantic segmentation tasks.

SemanticSegmentationInputTransform

segmentation.data.SegmentationMatplotlibVisualization

Process and show the image batch and its associated label using matplotlib.

segmentation.data.SemanticSegmentationInput

segmentation.data.SemanticSegmentationFilesInput

segmentation.data.SemanticSegmentationFolderInput

segmentation.data.SemanticSegmentationNumpyInput

segmentation.data.SemanticSegmentationTensorInput

segmentation.data.SemanticSegmentationFiftyOneInput

segmentation.data.SemanticSegmentationDeserializer

segmentation.model.SemanticSegmentationOutputTransform

segmentation.output.FiftyOneSegmentationLabelsOutput

A Output which converts the model outputs to FiftyOne segmentation format.

segmentation.output.SegmentationLabelsOutput

A Output which converts the model outputs to the label of the argmax classification per pixel in the image for semantic segmentation tasks.

segmentation.transforms.default_transforms

The default transforms for semantic segmentation: resize the image and mask, collate the batch, and apply normalization.

segmentation.transforms.prepare_target

Convert the target mask to long and remove the channel dimension.

segmentation.transforms.train_default_transforms

During training, we apply the default transforms with additional RandomHorizontalFlip and ColorJitter.

Style Transfer

StyleTransfer

StyleTransfer is a Task for transferring the style from one image onto another.

StyleTransferData

StyleTransferInputTransform

raise_not_supported

rtype

NoReturn

flash.image.data

ImageDeserializer

ImageNumpyInput

ImageTensorInput

Read the Docs v: latest
Versions
latest
stable
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
Downloads
html
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.