about norm2d_cx function

[WZMIAOMIAO]

Hi, In BatchNormalization, there should be four parameters(moving_mean, moving_var, beta, gamma), as far as I know .

but in https://github.com/facebookresearch/pycls/blob/master/pycls/models/blocks.py#L76, here only add two parameters.

def norm2d_cx(cx, w_in):
    """Accumulates complexity of norm2d into cx = (h, w, flops, params, acts)."""
    h, w, flops, params, acts = cx["h"], cx["w"], cx["flops"], cx["params"], cx["acts"]
    params += 2 * w_in
    return {"h": h, "w": w, "flops": flops, "params": params, "acts": acts}

Are there any other considerations?