MemoryError：无法为形状为 (15500, 2, 240, 240, 1) 且数据类型为 int16 的数组分配 3.33 GiB

Question

To run the code I'm using PyCharm latest version on a Windows 7 64bit with 16Gb of RAM and...

Python version: 3.7.7 (default, May  6 2020, 11:45:54) [MSC v.1916 64 bit (AMD64)]

I'm trying to load a lot of NIFTI images using SimplyITK and Numpy from the BraTS 2019 dataset .

This is the code I use to load the images into a numpy array.

import SimpleITK as sitk


def read_nifti_images(images_full_path):
    """ 
    Read nifti files from a gziped file.
  
    Read nifti files from a gziped file using SimpleITK library.
  
    Parameters: 
    images_full_path (string): Full path to gziped file including file name.
  
    Returns: 
    SimpleITK.SimpleITK.Image, numpy array: images read as image, images read as numpy array 
  
    """
    # Reads images using SimpleITK.
    images = sitk.ReadImage(images_full_path)
    # Get a numpy array from a SimpleITK Image.
    images_array = sitk.GetArrayFromImage(images)
    
    # More info about SimpleITK images: http://simpleitk.github.io/SimpleITK-Notebooks/01_Image_Basics.html
    
    return images, images_array

This code works fine with smallest dataset. I'm trying to load 518 nii.gz files with 155 images each file.

When I run the code, there are 4GiB of RAM used, and when it gets to 8GiB, it throws the exception.

Is there any way to load all the images in memory? Maybe there is a memory usage limitation in Windows and/or in PyCharm.

Answer 1

You have two copies of images in memory, a SimpleITK version and a numpy version. So when you hit 8 gig of images, you've really got 16 gig in memory, hence your crash.

You can try using sitk.GetArrayViewFromImage. That does not make a whole new copy of the image when converting from SimpleITK to numpy. It creates a numpy data structure that points to the same pixel buffer as the SimpleITK image.