Skip to content

translate_x

TranslateX

Bases: NumpyOp

Randomly shift the image along the X axis.

This is a wrapper for functionality provided by the PIL library: https://github.com/python-pillow/Pillow/tree/master/src/PIL.

Parameters:

Name Type Description Default
inputs Union[str, Iterable[str]]

Key(s) of images to be modified.

 required
outputs Union[str, Iterable[str]]

Key(s) into which to write the modified images.

 required
mode Union[None, str, Iterable[str]]

What mode(s) to execute this Op in. For example, "train", "eval", "test", or "infer". To execute regardless of mode, pass None. To execute in all modes except for a particular one, you can pass an argument like "!infer" or "!train".

 None
shift_limit float

Shift factor range as a fraction of image width. If shift_limit is a single float, the range will be (-shift_limit, shift_limit).

 0.2
Image types

uint8

Source code in fastestimator\fastestimator\op\numpyop\univariate\translate_x.py 
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
@traceable()
class TranslateX(NumpyOp):
    """Randomly shift the image along the X axis.

    This is a wrapper for functionality provided by the PIL library:
    https://github.com/python-pillow/Pillow/tree/master/src/PIL.

    Args:
        inputs: Key(s) of images to be modified.
        outputs: Key(s) into which to write the modified images.
        mode: What mode(s) to execute this Op in. For example, "train", "eval", "test", or "infer". To execute
            regardless of mode, pass None. To execute in all modes except for a particular one, you can pass an argument
            like "!infer" or "!train".
        shift_limit: Shift factor range as a fraction of image width. If shift_limit is a single float, the range will
            be (-shift_limit, shift_limit).

    Image types:
        uint8
    """
    def __init__(self,
                 inputs: Union[str, Iterable[str]],
                 outputs: Union[str, Iterable[str]],
                 mode: Union[None, str, Iterable[str]] = None,
                 shift_limit: float = 0.2):
        super().__init__(inputs=inputs, outputs=outputs, mode=mode)
        self.shift_limit = param_to_range(shift_limit)
        self.in_list, self.out_list = True, True

    def forward(self, data: List[np.ndarray], state: Dict[str, Any]) -> List[np.ndarray]:
        return [self._apply_translatex(elem) for elem in data]

    def _apply_translatex(self, data: np.ndarray) -> np.ndarray:
        im = Image.fromarray(data)
        width, height = im.size
        displacement = random.uniform(self.shift_limit[0] * width, self.shift_limit[1] * width)
        im = im.transform((width, height),
                          ImageTransform.AffineTransform((1.0, 0.0, displacement, 0.0, 1.0, 0.0)),
                          resample=Image.BICUBIC)
        return np.array(im)