Geometric functional transforms (augmentations.geometric.functional)¶
¶
def
albumentations.augmentations.geometric.functional.bbox_rot90(bbox, factor, rows, cols)
[view source on GitHub]
¶
Rotates a bounding box by 90 degrees CCW (see np.rot90)
Parameters:
Name | Type | Description |
---|---|---|
bbox |
tuple |
A bounding box tuple (x_min, y_min, x_max, y_max). |
factor |
int |
Number of CCW rotations. Must be in set {0, 1, 2, 3} See np.rot90. |
rows |
int |
Image rows. |
cols |
int |
Image cols. |
Returns:
Type | Description |
---|---|
tuple |
A bounding box tuple (x_min, y_min, x_max, y_max). |
def
albumentations.augmentations.geometric.functional.bbox_rotate(bbox, angle, rows, cols)
[view source on GitHub]
¶
Rotates a bounding box by angle degrees.
Parameters:
Name | Type | Description |
---|---|---|
bbox |
tuple |
A bounding box |
angle |
int |
Angle of rotation in degrees. |
rows |
int |
Image rows. |
cols |
int |
Image cols. |
Returns:
Type | Description |
---|---|
|
A bounding box |
def
albumentations.augmentations.geometric.functional.elastic_transform(img, alpha, sigma, alpha_affine, interpolation=1, border_mode=4, value=None, random_state=None, approximate=False)
[view source on GitHub]
¶
Elastic deformation of images as described in [Simard2003]_ (with modifications). Based on https://gist.github.com/erniejunior/601cdf56d2b424757de5
.. [Simard2003] Simard, Steinkraus and Platt, "Best Practices for Convolutional Neural Networks applied to Visual Document Analysis", in Proc. of the International Conference on Document Analysis and Recognition, 2003.
def
albumentations.augmentations.geometric.functional.keypoint_rot90(keypoint, factor, rows, cols, **params)
[view source on GitHub]
¶
Rotates a keypoint by 90 degrees CCW (see np.rot90)
Parameters:
Name | Type | Description |
---|---|---|
keypoint |
tuple |
A keypoint |
factor |
int |
Number of CCW rotations. Must be in range [0;3] See np.rot90. |
rows |
int |
Image height. |
cols |
int |
Image width. |
Returns:
Type | Description |
---|---|
tuple |
A keypoint |
Exceptions:
Type | Description |
---|---|
ValueError |
if factor not in set {0, 1, 2, 3} |
def
albumentations.augmentations.geometric.functional.keypoint_rotate(keypoint, angle, rows, cols, **params)
[view source on GitHub]
¶
Rotate a keypoint by angle.
Parameters:
Name | Type | Description |
---|---|---|
keypoint |
tuple |
A keypoint |
angle |
float |
Rotation angle. |
rows |
int |
Image height. |
cols |
int |
Image width. |
Returns:
Type | Description |
---|---|
tuple |
A keypoint |
def
albumentations.augmentations.geometric.functional.keypoint_scale(keypoint, scale_x, scale_y)
[view source on GitHub]
¶
Scales a keypoint by scale_x and scale_y.
Parameters:
Name | Type | Description |
---|---|---|
keypoint |
Sequence[float] |
A keypoint |
scale_x |
float |
Scale coefficient x-axis. |
scale_y |
float |
Scale coefficient y-axis. |
Returns:
Type | Description |
---|---|
|
A keypoint |
def
albumentations.augmentations.geometric.functional.py3round(number)
[view source on GitHub]
¶
Unified rounding in all python versions.