MemoryError: 无法为 DIPY 图像配准中具有形状 (344, 344, 127) 和数据类型 float64 的数组分配 115. MiB

Question

我正在尝试使用 DIPY（3d 中的仿射注册）进行图像注册我尝试运行以下代码（实际上我尝试使用不同的 nifti 文件重现示例代码）

from os.path import join as pjoin
import numpy as np
from dipy.viz import regtools
from dipy.data import fetch_mni_template, read_mni_template
from dipy.data.fetcher import fetch_syn_data, read_syn_data
from dipy.io.image import load_nifti
from dipy.align.imaffine import (transform_centers_of_mass,
                                 AffineMap,
                                 MutualInformationMetric,
                                 AffineRegistration)
from dipy.align.transforms import (TranslationTransform3D,
                                   RigidTransform3D,
                                   AffineTransform3D)

files, folder = fetch_mni_template()
static_data, static_affine = load_nifti(pjoin(folder, 'mni_icbm152_t1_tal_nlin_asym_09a.nii'))
static = np.squeeze(static_data)
static_grid2world = static_affine

files, folder = fetch_syn_data()
moving_data, moving_affine = load_nifti(pjoin(folder, '2018.nii'))
moving = moving_data
moving_grid2world = moving_affine

identity = np.eye(4)
affine_map = AffineMap(identity,
                       static.shape, static_grid2world,
                       moving.shape, moving_grid2world)
print(static.shape)


resampled = affine_map.transform(moving)


regtools.overlay_slices(static, resampled, None, 0,
                        "Static", "Moving", "resampled_0.png")
regtools.overlay_slices(static, resampled, None, 1,
                        "Static", "Moving", "resampled_1.png")
regtools.overlay_slices(static, resampled, None, 2,
                        "Static", "Moving", "resampled_2.png")

c_of_mass = transform_centers_of_mass(static, static_grid2world,
                                      moving, moving_grid2world)

transformed = c_of_mass.transform(moving)
regtools.overlay_slices(static, transformed, None, 0,
                        "Static", "Transformed", "transformed_com_0.png")
regtools.overlay_slices(static, transformed, None, 1,
                        "Static", "Transformed", "transformed_com_1.png")
regtools.overlay_slices(static, transformed, None, 2,
                        "Static", "Transformed", "transformed_com_2.png")

nbins = 32
sampling_prop = None
metric = MutualInformationMetric(nbins, sampling_prop)

level_iters = [10000, 1000, 100]

sigmas = [3.0, 1.0, 0.0]

factors = [4, 2, 1]

affreg = AffineRegistration(metric=metric,
                            level_iters=level_iters,
                            sigmas=sigmas,
                            factors=factors)

transform = TranslationTransform3D()
params0 = None
starting_affine = c_of_mass.affine

translation = affreg.optimize(static, moving, transform, params0,
                              static_grid2world, moving_grid2world,
                              starting_affine=starting_affine)

但我收到以下错误

内存错误：无法为形状为 (344, 344, 127) 且数据类型为 float64 的数组分配 115. MiB

我找不到解决方案。

Answer 1

我通过从 32 位版本的 python 移动到 64 位版本解决了这个问题

谢谢，玛尼