我想计算两个 numpy 直方图之间的距离

Question

我正在创建一个图像处理程序，我想测量两个 numpy 直方图之间的 wasserstein 距离。这两个直方图是用函数numpy.histogram创建的

我像这样从 scipy.stats 包中尝试了 wasserstein_distance

from scipy.stats import wasserstein_distance 

wasserstein_distance(histogram1,histogram2)

但它给了我那个错误

ValueError：使用序列设置数组元素。

完整代码：

首先是计算距离的函数：

    def f_dist( histogram1 ,histogram2):

    return wasserstein_distance(histogram1,histogram2)

比计算直方图创建掩码的函数：

def prepare_mask(polygon, image,value):

"""Returns binary mask based on input polygon presented as list of coordinates of vertices

Params:

    polygon (list) - coordinates of polygon's vertices. Ex: [(x1,y1),(x2,y2),...] or [x1,y1,x2,y2,...]

    image (numpy array) - original image. Will be used to create mask of the same size. Shape (H, W, C).

Output:

    mask (numpy array) - boolean mask. Shape (H, W).

"""

# create an "empty" pre-mask with the same size as original image

width = image.shape[1]

height = image.shape[0]

mask = Image.new('L', (width, height),value )

# Draw your mask based on polygon

ImageDraw.Draw(mask).polygon(polygon, outline=1, fill=abs(value-1))

# Covert to np array

mask = np.array(mask).astype(bool)

return mask

比创建直方图的函数

def compute_histogram(mask, image):

"""Returns histogram for image region defined by mask for each channel

Params:

    image (numpy array) - original image. Shape (H, W, C).

    mask (numpy array) - boolean mask. Shape (H, W).

Output:

    list of tuples, each tuple (each channel) contains 2 arrays: first - computed histogram, the second - bins.

"""

# Apply binary mask to your array, you will get array with shape (N, C)

region = image[mask]

hist = np.histogram(region.ravel(), bins=256, range=[0, 255])

return hist

Answer 1

感谢 SpghttCd 解决方案很简单......我只需要更换wasserstein_distance(histogram1, histogram2)和wasserstein_distance(histogram1[0], histogram2[0])