pascal_voc_tools.Augmenter package

Submodules

pascal_voc_tools.Augmenter.bbox_util module

pascal_voc_tools.Augmenter.bbox_util.bbox_area(bbox)
pascal_voc_tools.Augmenter.bbox_util.clip_box(bbox, clip_box, alpha)

Clip the bounding boxes to the borders of an image

Parameters:
  • bbox (numpy.ndarray) – Numpy array containing bounding boxes of shape N X 4 where N is the number of bounding boxes and the bounding boxes are represented in the format x1 y1 x2 y2
  • clip_box (numpy.ndarray) – An array of shape (4,) specifying the diagonal co-ordinates of the image The coordinates are represented in the format x1 y1 x2 y2
  • alpha (float) – If the fraction of a bounding box left in the image after being clipped is less than alpha the bounding box is dropped.
Returns:

Numpy array containing clipped bounding boxes of shape N X 4 where N is the number of bounding boxes left are being clipped and the bounding boxes are represented in the format x1 y1 x2 y2
Return type:

numpy.ndarray
pascal_voc_tools.Augmenter.bbox_util.draw_rect(im, cords, color=None)

Draw the rectangle on the image

Parameters:
  • im (numpy.ndarray) – numpy image
  • cords (numpy.ndarray) – Numpy array containing bounding boxes of shape N X 4 where N is the number of bounding boxes and the bounding boxes are represented in the format x1 y1 x2 y2
Returns:

numpy image with bounding boxes drawn on it
Return type:

numpy.ndarray
pascal_voc_tools.Augmenter.bbox_util.get_corners(bboxes)

Get corners of bounding boxes

Parameters:bboxes (numpy.ndarray) – Numpy array containing bounding boxes of shape N X 4 where N is the number of bounding boxes and the bounding boxes are represented in the format x1 y1 x2 y2
Returns:Numpy array of shape N x 8 containing N bounding boxes each described by their corner co-ordinates x1 y1 x2 y2 x3 y3 x4 y4
Return type:numpy.ndarray
pascal_voc_tools.Augmenter.bbox_util.get_enclosing_box(corners)

Get an enclosing box for ratated corners of a bounding box

Parameters:corners (numpy.ndarray) – Numpy array of shape N x 8 containing N bounding boxes each described by their corner co-ordinates x1 y1 x2 y2 x3 y3 x4 y4
Returns:Numpy array containing enclosing bounding boxes of shape N X 4 where N is the number of bounding boxes and the bounding boxes are represented in the format x1 y1 x2 y2
Return type:numpy.ndarray
pascal_voc_tools.Augmenter.bbox_util.letterbox_image(img, inp_dim)

resize image with unchanged aspect ratio using padding

Parameters:
  • img (numpy.ndarray) – Image
  • inp_dim (tuple(int)) – shape of the reszied image
Returns:

Resized image
Return type:

numpy.ndarray
pascal_voc_tools.Augmenter.bbox_util.rotate_box(corners, angle, cx, cy, h, w)

Rotate the bounding box.

Parameters:
  • corners (numpy.ndarray) – Numpy array of shape N x 8 containing N bounding boxes each described by their corner co-ordinates x1 y1 x2 y2 x3 y3 x4 y4
  • angle (float) – angle by which the image is to be rotated
  • cx (int) – x coordinate of the center of image (about which the box will be rotated)
  • cy (int) – y coordinate of the center of image (about which the box will be rotated)
  • h (int) – height of the image
  • w (int) – width of the image
Returns:

Numpy array of shape N x 8 containing N rotated bounding boxes each described by their corner co-ordinates x1 y1 x2 y2 x3 y3 x4 y4
Return type:

numpy.ndarray
pascal_voc_tools.Augmenter.bbox_util.rotate_im(image, angle)

Rotate the image.

Rotate the image such that the rotated image is enclosed inside the tightest rectangle. The area not occupied by the pixels of the original image is colored black.

Parameters:
  • image (numpy.ndarray) – numpy image
  • angle (float) – angle by which the image is to be rotated
Returns:

Rotated Image
Return type:

numpy.ndarray

pascal_voc_tools.Augmenter.data_aug module

class pascal_voc_tools.Augmenter.data_aug.HorizontalFlip

Bases: object

Randomly horizontally flips the Image with the probability p

Parameters:p (float) – The probability with which the image is flipped
Returns:
  • numpy.ndaaray – Flipped image in the numpy format of shape HxWxC
  • numpy.ndarray – Tranformed bounding box co-ordinates of the format n x 4 where n is number of bounding boxes and 4 represents x1,y1,x2,y2 of the box
class pascal_voc_tools.Augmenter.data_aug.RandomHSV(hue=None, saturation=None, brightness=None)

Bases: object

HSV Transform to vary hue saturation and brightness

Hue has a range of 0-179 Saturation and Brightness have a range of 0-255. Chose the amount you want to change thhe above quantities accordingly.

Parameters:
  • hue (None or int or tuple (int)) – If None, the hue of the image is left unchanged. If int, a random int is uniformly sampled from (-hue, hue) and added to the hue of the image. If tuple, the int is sampled from the range specified by the tuple.
  • saturation (None or int or tuple(int)) – If None, the saturation of the image is left unchanged. If int, a random int is uniformly sampled from (-saturation, saturation) and added to the hue of the image. If tuple, the int is sampled from the range specified by the tuple.
  • brightness (None or int or tuple(int)) – If None, the brightness of the image is left unchanged. If int, a random int is uniformly sampled from (-brightness, brightness) and added to the hue of the image. If tuple, the int is sampled from the range specified by the tuple.
Returns:

  • numpy.ndaaray – Transformed image in the numpy format of shape HxWxC
  • numpy.ndarray – Resized bounding box co-ordinates of the format n x 4 where n is number of bounding boxes and 4 represents x1,y1,x2,y2 of the box
class pascal_voc_tools.Augmenter.data_aug.RandomHorizontalFlip(p=0.5)

Bases: object

Randomly horizontally flips the Image with the probability p

Parameters:p (float) – The probability with which the image is flipped
Returns:
  • numpy.ndaaray – Flipped image in the numpy format of shape HxWxC
  • numpy.ndarray – Tranformed bounding box co-ordinates of the format n x 4 where n is number of bounding boxes and 4 represents x1,y1,x2,y2 of the box
class pascal_voc_tools.Augmenter.data_aug.RandomRotate(angle=10)

Bases: object

Randomly rotates an image

Bounding boxes which have an area of less than 25% in the remaining in the transformed image is dropped. The resolution is maintained, and the remaining area if any is filled by black color.

Parameters:angle (float or tuple(float)) – if float, the image is rotated by a factor drawn randomly from a range (-angle, angle). If tuple, the angle is drawn randomly from values specified by the tuple
Returns:
  • numpy.ndaaray – Rotated image in the numpy format of shape HxWxC
  • numpy.ndarray – Tranformed bounding box co-ordinates of the format n x 4 where n is number of bounding boxes and 4 represents x1,y1,x2,y2 of the box
class pascal_voc_tools.Augmenter.data_aug.RandomScale(scale=0.2, diff=False)

Bases: object

Randomly scales an image

Bounding boxes which have an area of less than 25% in the remaining in the transformed image is dropped. The resolution is maintained, and the remaining area if any is filled by black color.

Parameters:scale (float or tuple(float)) – if float, the image is scaled by a factor drawn randomly from a range (1 - scale , 1 + scale). If tuple, the scale is drawn randomly from values specified by the tuple
Returns:
  • numpy.ndaaray – Scaled image in the numpy format of shape HxWxC
  • numpy.ndarray – Tranformed bounding box co-ordinates of the format n x 4 where n is number of bounding boxes and 4 represents x1,y1,x2,y2 of the box
class pascal_voc_tools.Augmenter.data_aug.RandomShear(shear_factor=0.2)

Bases: object

Randomly shears an image in horizontal direction

Bounding boxes which have an area of less than 25% in the remaining in the transformed image is dropped. The resolution is maintained, and the remaining area if any is filled by black color.

Parameters:shear_factor (float or tuple(float)) – if float, the image is sheared horizontally by a factor drawn randomly from a range (-shear_factor, shear_factor). If tuple, the shear_factor is drawn randomly from values specified by the tuple
Returns:
  • numpy.ndaaray – Sheared image in the numpy format of shape HxWxC
  • numpy.ndarray – Tranformed bounding box co-ordinates of the format n x 4 where n is number of bounding boxes and 4 represents x1,y1,x2,y2 of the box
class pascal_voc_tools.Augmenter.data_aug.RandomTranslate(translate=0.2, diff=False)

Bases: object

Randomly Translates the image

Bounding boxes which have an area of less than 25% in the remaining in the transformed image is dropped. The resolution is maintained, and the remaining area if any is filled by black color.

Parameters:translate (float or tuple(float)) – if float, the image is translated by a factor drawn randomly from a range (1 - translate , 1 + translate). If tuple, translate is drawn randomly from values specified by thetuple
Returns:
  • numpy.ndaaray – Translated image in the numpy format of shape HxWxC
  • numpy.ndarray – Tranformed bounding box co-ordinates of the format n x 4 where n is number of bounding boxes and 4 represents x1,y1,x2,y2 of the box
class pascal_voc_tools.Augmenter.data_aug.Resize(inp_dim)

Bases: object

Resize the image in accordance to image_letter_box function in darknet

The aspect ratio is maintained. The longer side is resized to the input size of the network, while the remaining space on the shorter side is filled with black color. This should be the last transform

Parameters:inp_dim (tuple(int)) – tuple containing the size to which the image will be resized.
Returns:
  • numpy.ndaaray – Sheared image in the numpy format of shape HxWxC
  • numpy.ndarray – Resized bounding box co-ordinates of the format n x 4 where n is number of bounding boxes and 4 represents x1,y1,x2,y2 of the box
class pascal_voc_tools.Augmenter.data_aug.Rotate(angle)

Bases: object

Rotates an image

Bounding boxes which have an area of less than 25% in the remaining in the transformed image is dropped. The resolution is maintained, and the remaining area if any is filled by black color.

Parameters:angle (float) – The angle by which the image is to be rotated
Returns:
  • numpy.ndaaray – Rotated image in the numpy format of shape HxWxC
  • numpy.ndarray – Tranformed bounding box co-ordinates of the format n x 4 where n is number of bounding boxes and 4 represents x1,y1,x2,y2 of the box
class pascal_voc_tools.Augmenter.data_aug.Scale(scale_x=0.2, scale_y=0.2)

Bases: object

Scales the image

Bounding boxes which have an area of less than 25% in the remaining in the transformed image is dropped. The resolution is maintained, and the remaining area if any is filled by black color.

Parameters:
  • scale_x (float) – The factor by which the image is scaled horizontally
  • scale_y (float) – The factor by which the image is scaled vertically
Returns:

  • numpy.ndaaray – Scaled image in the numpy format of shape HxWxC
  • numpy.ndarray – Tranformed bounding box co-ordinates of the format n x 4 where n is number of bounding boxes and 4 represents x1,y1,x2,y2 of the box
class pascal_voc_tools.Augmenter.data_aug.Sequence(augmentations, probs=1)

Bases: object

Initialise Sequence object

Apply a Sequence of transformations to the images/boxes.

Parameters:
  • augemnetations (list) – List containing Transformation Objects in Sequence they are to be applied
  • probs (int or list) – If int, the probability with which each of the transformation will be applied. If list, the length must be equal to augmentations. Each element of this list is the probability with which each corresponding transformation is applied
Returns:

Sequence Object
Return type:

Sequence
class pascal_voc_tools.Augmenter.data_aug.Shear(shear_factor=0.2)

Bases: object

Shears an image in horizontal direction

Bounding boxes which have an area of less than 25% in the remaining in the transformed image is dropped. The resolution is maintained, and the remaining area if any is filled by black color.

Parameters:shear_factor (float) – Factor by which the image is sheared in the x-direction
Returns:
  • numpy.ndaaray – Sheared image in the numpy format of shape HxWxC
  • numpy.ndarray – Tranformed bounding box co-ordinates of the format n x 4 where n is number of bounding boxes and 4 represents x1,y1,x2,y2 of the box
class pascal_voc_tools.Augmenter.data_aug.Translate(translate_x=0.2, translate_y=0.2, diff=False)

Bases: object

Randomly Translates the image

Bounding boxes which have an area of less than 25% in the remaining in the transformed image is dropped. The resolution is maintained, and the remaining area if any is filled by black color.

Parameters:translate (float or tuple(float)) – if float, the image is translated by a factor drawn randomly from a range (1 - translate , 1 + translate). If tuple, translate is drawn randomly from values specified by the tuple
Returns:
  • numpy.ndaaray – Translated image in the numpy format of shape HxWxC
  • numpy.ndarray – Tranformed bounding box co-ordinates of the format n x 4 where n is number of bounding boxes and 4 represents x1,y1,x2,y2 of the box

Module contents