torchio.data.sampler.uniform.UniformSampler.__call__() - Code Metrics - Inspection of "Faster implementation for UniformSampler" - fepegar/torchio - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Pull Request — master (#296)

by Fernando

created 2020-09-17 18:47 UTC

UniformSampler.call() A

↳ Parent: torchio.data.sampler.uniform

Complexity

Conditions

Size

Total Lines	14
Code Lines	10

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	2
eloc	10
nop	2
dl	0
loc	14
rs	9.9
c	0
b	0
f	0

import torch
from ...data.subject import Subject
from ...torchio import TypePatchSize
from .sampler import RandomSampler
from typing import Optional, Tuple, Generator
import numpy as np


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

    Args:
        patch_size: See :py:class:`~torchio.data.PatchSampler`.
    """
    def __init__(self, patch_size: TypePatchSize):
        super().__init__(patch_size, None)

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

    def __call__(self, sample: Subject) -> Generator[Subject, None, None]:
        sample.check_consistent_spatial_shape()

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

        valid_range = sample.spatial_shape - self.patch_size
        index_ini = [torch.randint(x + 1, (1,)).item() for x in valid_range]
        index_ini_array = np.asarray(index_ini)
        yield self.extract_patch(sample, index_ini_array)


1			import torch
2			from ...data.subject import Subject
3			from ...torchio import TypePatchSize
4			from .sampler import RandomSampler
5			from typing import Optional, Tuple, 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 :py:class:`~torchio.data.PatchSampler`.
14			"""
15			def __init__(self, patch_size: TypePatchSize):
16			super().__init__(patch_size, None)
17
18			def get_probability_map(self, sample: Subject) -> torch.Tensor:
19			return torch.ones(1, *sample.spatial_shape)
20
21			def __call__(self, sample: Subject) -> Generator[Subject, None, None]:
22			sample.check_consistent_spatial_shape()
23
24			if np.any(self.patch_size > sample.spatial_shape):
25			message = (
26			f'Patch size {tuple(self.patch_size)} cannot be'
27			f' larger than image size {tuple(sample.spatial_shape)}'
28			)
29			raise RuntimeError(message)
30
31			valid_range = sample.spatial_shape - self.patch_size
32			index_ini = [torch.randint(x + 1, (1,)).item() for x in valid_range]
33			index_ini_array = np.asarray(index_ini)
34			yield self.extract_patch(sample, index_ini_array)
35

fepegar / torchio

Pull Request — master (#296)

UniformSampler.__call__() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like

UniformSampler.call() A