torchio.data.sampler.uniform.UniformSampler.__call__() - Code Metrics - Inspection of "Remove methods with unnecessary super delegation...." - fepegar/torchio - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — master ( 672991...862c9a )

by Fernando

created 2021-04-21 22:49 UTC

UniformSampler.call() B

↳ Parent: torchio.data.sampler.uniform

Complexity

Conditions

Size

Total Lines	25
Code Lines	19

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	5
eloc	19
nop	3
dl	0
loc	25
rs	8.9833
c	0
b	0
f	0

import torch
from ...data.subject import Subject
from ...typing import TypePatchSize
from .sampler import RandomSampler
from typing import Generator
import numpy as np


class UniformSampler(RandomSampler):
    """Randomly extract patches from a volume with uniform probability.

    Args:
        patch_size: See :class:`~torchio.data.PatchSampler`.
    """

    def get_probability_map(self, subject: Subject) -> torch.Tensor:
        return torch.ones(1, *subject.spatial_shape)

    def __call__(
            self,
            subject: Subject,
            num_patches: int = None,
            ) -> Generator[Subject, None, None]:
        subject.check_consistent_spatial_shape()

        if np.any(self.patch_size > subject.spatial_shape):
            message = (
                f'Patch size {tuple(self.patch_size)} cannot be'
                f' larger than image size {tuple(subject.spatial_shape)}'
            )
            raise RuntimeError(message)

        valid_range = subject.spatial_shape - self.patch_size
        patches_left = num_patches if num_patches is not None else True
        while patches_left:
            index_ini = [
                torch.randint(x + 1, (1,)).item()
                for x in valid_range
            ]
            index_ini_array = np.asarray(index_ini)
            yield self.extract_patch(subject, index_ini_array)
            if num_patches is not None:
                patches_left -= 1


1			import torch
2			from ...data.subject import Subject
3			from ...typing import TypePatchSize
4			from .sampler import RandomSampler
5			from typing import Generator
6			import numpy as np
7
8
9			class UniformSampler(RandomSampler):
10			"""Randomly extract patches from a volume with uniform probability.
11
12			Args:
13			patch_size: See :class:`~torchio.data.PatchSampler`.
14			"""
15
16			def get_probability_map(self, subject: Subject) -> torch.Tensor:
17			return torch.ones(1, *subject.spatial_shape)
18
19			def __call__(
20			self,
21			subject: Subject,
22			num_patches: int = None,
23			) -> Generator[Subject, None, None]:
24			subject.check_consistent_spatial_shape()
25
26			if np.any(self.patch_size > subject.spatial_shape):
27			message = (
28			f'Patch size {tuple(self.patch_size)} cannot be'
29			f' larger than image size {tuple(subject.spatial_shape)}'
30			)
31			raise RuntimeError(message)
32
33			valid_range = subject.spatial_shape - self.patch_size
34			patches_left = num_patches if num_patches is not None else True
35			while patches_left:
36			index_ini = [
37			torch.randint(x + 1, (1,)).item()
38			for x in valid_range
39			]
40			index_ini_array = np.asarray(index_ini)
41			yield self.extract_patch(subject, index_ini_array)
42			if num_patches is not None:
43			patches_left -= 1
44

fepegar / torchio

Push — master ( 672991...862c9a )

UniformSampler.__call__() B

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like

UniformSampler.call() B