Open renchenliang opened 5 years ago
p_min = np.amin(shrink_xy_list, axis=0) p_max = np.amax(shrink_xy_list, axis=0)
ith = point_inside_of_nth_quad(px, py, shrink_xy_list, shrink_1, long_edge) vs = [[[3, 0], [1, 2]], [[0, 1], [2, 3]]] if ith in range(2): gt[i, j, 1] = 1 if ith == 0:
感觉这里的shrink_xy_list范围应该改成如下 p_min = np.amin(xy_list, axis=0) p_max = np.amax(xy_list, axis=0) ith = point_inside_of_nth_quad(px, py, xy_list, shrink_1, long_edge) vs = [[[3, 0], [1, 2]], [[0, 1], [2, 3]]] if ith in range(2):
感觉原来的label与你给出的预训练模型的结果有点出入。 不知道我提供的这个label的修改是否有错误
p_min = np.amin(shrink_xy_list, axis=0) p_max = np.amax(shrink_xy_list, axis=0)
ith = point_inside_of_nth_quad(px, py, shrink_xy_list, shrink_1, long_edge) vs = [[[3, 0], [1, 2]], [[0, 1], [2, 3]]] if ith in range(2): gt[i, j, 1] = 1 if ith == 0:
感觉这里的shrink_xy_list范围应该改成如下 p_min = np.amin(xy_list, axis=0) p_max = np.amax(xy_list, axis=0) ith = point_inside_of_nth_quad(px, py, xy_list, shrink_1, long_edge) vs = [[[3, 0], [1, 2]], [[0, 1], [2, 3]]] if ith in range(2):
感觉原来的label与你给出的预训练模型的结果有点出入。 不知道我提供的这个label的修改是否有错误