num_rays(N) is 2073600, num_sigmas is 2073728?

[T_T]

1 run ''python main_nerf data/nerf_synthetic/chair --workspace chair -O --bound 1.0 --scale 0.8 --dt_gamma 0 --gui''
2. code in nerf/renderer.py
3. questions:
N = rays_o.shape[0] //N=2073600
...
while step < max_steps: //step==1
xyzs, dirs, deltas = raymarching.march_rays(...) //xyzs==Tensor(2073728,3)
sigmas, rgbs= self(xyzs, dirs) //rgbs==Tensor(2073728,3), sigmas ==Tensor(2073728,1)
4. Why the number of generated sigmas will be 128 more than the number of rays？