i have following code compute hog image 8 bins , pre-counted sobel x , y filtered image:
for y in xrange(0, 480): x in xrange(0, 640): base_angle = np.arctan2(sobel_y[y,x], sobel_x[y,x]) * 180/np.pi if base_angle < 0: base_angle += 360 angle = int(round(base_angle / 45)) if angle == 8: angle = 0 hog[y,x,angle] += np.sqrt(sobel_x[y,x]**2 + sobel_y[y,x]**2) i trying modify avoid loops:
base_angle = np.arctan2(sobel_y, sobel_x) * 180/np.pi base_angle[base_angle < 0] += 360 angle =(base_angle / 45).round().astype(np.uint8) angle[angle == bins] = 0 hog[:,:,angle] += np.sqrt(sobel_x**2 + sobel_y**2) however, last expression not count correctly. need have magnitude (np.sqrt... expression) being added hog array according index angle array, @ every (y,x) point of hog array. solutions?
use
magnitude = np.sqrt(sobel_x**2 + sobel_y**2) y, x = np.ogrid[0:angle.shape[0], 0:angle.shape[1]] hog[y, x, angle] += magnitude to update hog.
import numpy np def using_for_loop(hog, sobel_y, sobel_x): y in xrange(0, sobel_y.shape[0]): x in xrange(0, sobel_x.shape[1]): base_angle = np.arctan2(sobel_y[y, x], sobel_x[y, x]) * 180 / np.pi if base_angle < 0: base_angle += 360 angle = int(round(base_angle / 45)) if angle == 8: angle = 0 hog[y, x, angle] += np.sqrt(sobel_x[y, x] ** 2 + sobel_y[y, x] ** 2) return hog def using_indexing(hog, sobel_y, sobel_x): base_angle = np.arctan2(sobel_y, sobel_x) * 180 / np.pi base_angle[base_angle < 0] += 360 angle = (base_angle / 45).round().astype(np.uint8) angle[angle == bins] = 0 magnitude = np.sqrt(sobel_x ** 2 + sobel_y ** 2) y, x = np.ogrid[0:angle.shape[0], 0:angle.shape[1]] hog[y, x, angle] += magnitude return hog bins = 8 sobel_y, sobel_x = np.meshgrid([1, 2, 3], [4, 5, 6, 7]) # hog = np.zeros(sobel_x.shape + (bins,)) hog = np.random.random(sobel_x.shape + (bins,)) answer = using_for_loop(hog, sobel_y, sobel_x) result = using_indexing(hog, sobel_y, sobel_x) assert np.allclose(answer, result) note if
in [62]: angle.shape out[62]: (4, 3) then
in [74]: hog[:,:,angle].shape out[74]: (4, 3, 4, 3) that's not right shape. rather, if define
in [75]: y, x = np.ogrid[0:angle.shape[0], 0:angle.shape[1]] then hog[y, x, angle] has same shape magnitude:
in [76]: hog[y, x, angle].shape out[76]: (4, 3) in [77]: magnitude = np.sqrt(sobel_x ** 2 + sobel_y ** 2) in [78]: magnitude.shape out[78]: (4, 3) of course, not proof hog[y, x, angle] correct expression, equivalent of physicist's dimensionality check shows @ least on right track.
with numpy fancy indexing, when y, x, , angle have same shape (or broadcast same shape),
hog[y, x, angle] will of same shape. (i,j)th element in hog[y, x, angle] equal
hog[y[i,j], x[i,j], angle[i,j]] this why hog[y, x, angle] += magnitude works.
Comments
Post a Comment