torchio.data.sampler.uniform.UniformSampler.__call__() - Code Metrics - Inspection of "Make the grid sampler compatible with the queue (#..." - fepegar/torchio - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — master ( c9c9a5...7d9f03 )

by Fernando

created 2021-05-10 09:10 UTC

torchio.data.sampler.uniform.UniformSampler.call() B

↳ Parent: Project

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 .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 _generate_patches(
            self,
            subject: Subject,
            num_patches: int = None,
            ) -> Generator[Subject, None, None]:
        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 .sampler import RandomSampler
4			from typing import Generator
5			import numpy as np
6
7
8			class UniformSampler(RandomSampler):
9			"""Randomly extract patches from a volume with uniform probability.
10
11			Args:
12			patch_size: See :class:`~torchio.data.PatchSampler`.
13			"""
14
15			def get_probability_map(self, subject: Subject) -> torch.Tensor:
16			return torch.ones(1, *subject.spatial_shape)
17
18			def _generate_patches(
19			self,
20			subject: Subject,
21			num_patches: int = None,
22			) -> Generator[Subject, None, None]:
23			valid_range = subject.spatial_shape - self.patch_size
24			patches_left = num_patches if num_patches is not None else True
25			while patches_left:
26			index_ini = [
27			torch.randint(x + 1, (1,)).item()
28			for x in valid_range
29			]
30			index_ini_array = np.asarray(index_ini)
31			yield self.extract_patch(subject, index_ini_array)
32			if num_patches is not None:
33			patches_left -= 1
34

fepegar / torchio

Push — master ( c9c9a5...7d9f03 )

torchio.data.sampler.uniform.UniformSampler.__call__() B

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like

torchio.data.sampler.uniform.UniformSampler.call() B