8.1.2.11. blueoil.tfds_pre_processor

8.1.2.11.1. Module Contents

8.1.2.11.1.1. Classes

TFDSResize

Resize an image

TFDSPerImageStandardization

Standardization per image.

TFDSResizeWithGtBoxes

Resize image with gt boxes.

TFDSDivideBy255

Divide image by 255

8.1.2.11.1.2. Functions

tfds_resize_with_gt_boxes(image, gt_boxes, size=(256, 256))

Resize an image and gt_boxes.
blueoil.tfds_pre_processor.tfds_resize_with_gt_boxes(image, gt_boxes, size=(256, 256))

Resize an image and gt_boxes.

Parameters

  • image (tf.Tensor) – image with 3 dim

  • gt_boxes (tf.Tensor) – Ground truth boxes in the image. shape is [num_boxes, 5(x, y, width, height, class_id)].

  • size – [height, width]

class blueoil.tfds_pre_processor.TFDSResize(size=(256, 256))

Bases: blueoil.data_processor.Processor

Resize an image

__call__(self, image, **kwargs)
Parameters

image (tf.Tensor) – an image tensor sized (orig_height, orig_width, channel)

class blueoil.tfds_pre_processor.TFDSPerImageStandardization

Bases: blueoil.data_processor.Processor

Standardization per image.

__call__(self, image, **kwargs)

Call processor method for each a element of data.

Return image and labels etc.

class blueoil.tfds_pre_processor.TFDSResizeWithGtBoxes(size)

Bases: blueoil.data_processor.Processor

Resize image with gt boxes.

Parameters

size – Target size.

__call__(self, image, gt_boxes=None, **kwargs)

Call processor method for each a element of data.

Return image and labels etc.

class blueoil.tfds_pre_processor.TFDSDivideBy255

Bases: blueoil.data_processor.Processor

Divide image by 255

__call__(self, image, **kwargs)

Call processor method for each a element of data.

Return image and labels etc.