Four Thirds Variance

Ioffe and Szegedy's Algorithm 2 turns a trained BatchNorm layer into a fixed transform at inference:

$\mathrm{Var}[x] \leftarrow \frac{m}{m-1}, \mathrm{E}${\mathcal{B}}[\sigma{\mathcal{B}}^2], \qquad y = \frac{\gamma}{\sqrt{\mathrm{Var}[x]+\epsilon}}, x + \left(\beta - \frac{\gamma,\mathrm{E}[x]}{\sqrt{\mathrm{Var}[x]+\epsilon}}\right)

For one channel, trained with minibatch size $m=4$: the averaged minibatch variance $\mathrm{E}${\mathcal{B}}[\sigma{\mathcal{B}}^2] = 0.75, $\mathrm{E}[x] = 1$, $\gamma = 2$, $\beta = 0.5$, $\epsilon \approx 0$.

What does this layer compute at inference?