3d prediction plot

[chunniunai220ml]

hi, thank for ur brilliant repo!

when i draw 3d prediction image refer ur render_animation() function, like this def render3d(pose): fig = plt.figure() ax_in = fig.add_subplot(111, projection='3d') ax_in.view_init(elev=15., azim=70) ax_in.get_xaxis().set_visible(False) ax_in.get_yaxis().set_visible(False) ax_in.set_axis_off() ax_3d = [] lines_3d = [] ax_3d.append(ax_in) lines_3d.append([]) parents=[-1, 0, 1, 2, 0, 4, 5, 0, 7, 8, 9, 8, 11, 12, 8, 14, 15] index = [i for i in np.arange(17)] for j, j_parent in zip(index, parents): if j_parent == -1: continue for n, ax in enumerate(ax_3d):

        lines_3d[n].append(ax.plot([pose[j, 0], pose[j_parent, 0]],
                            [pose[j, 1], pose[j_parent, 1]],
                            [pose[j, 2], pose[j_parent, 2]],  c='g', linewidth=2))
# ax_in.view_init(elev=15., azim=70)
plt.show()
plt.imshow(fig)
plt.savefig('oric3d.jpg')
plt.close()

but the result is not like ur visualization results.

why i do not do normalize_screen_coordinates function, the prediction is not well, like above picture?