AttributeError: 'Renderer' object has no attribute 'call_depth_function'

[zParquet]

Thanks for your excellent work!
I have a small question about the training mode of "onsurf_render", in the line 323 in model/rendering.py:

self.model.eval()
with torch.no_grad():
    d_i = self.call_depth_function(camera_world, ray_vector, self.model, it=8, n_steps=[int(512),int(512)+1], check_unitsphere_intersection=True, rad=rad)

It seems that there is no implementation for "self.call_depth_function" here. Could you please tell me where is the source code of "call_depth_function" or how does this function work?
Thanks a lot!