New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

about norm2d_cx function #147

Open

WZMIAOMIAO opened this issue Jun 2, 2021 · 0 comments

WZMIAOMIAO commented Jun 2, 2021

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?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment