// with math_img from nilearn
from nilearn.image import math_img
original_voxels = math_img("np.sum(img)", img=ward.mask_img_).get_data()
// common vmin and vmax
vmin = math_img("np.min(img)", img=mean_func_img).get_data()
vmax = math_img("np.max(img)", img=mean_func_img).get_data()
After Change
// Grab number of voxels from attribute mask image (mask_img_).
import numpy as np
original_voxels = np.sum(ward.mask_img_.get_data())
// Compute mean over time on the functional image to use the mean
// image for compressed representation comparisons
