BatchNorm Layer: it seems to be safer to add a epsilon to the standard deviation

[cook]

In the following codes cited from the file src/layer/batchnorm, if the sqrt_var is zero, there will be a zero-division error. So I advice to add a epsilon to the standard deviation or add some protection codes.

    float sqrt_var = sqrt(var_data[i]);
    a_data[i] = bias_data[i] - slope_data[i] * mean_data[i] / sqrt_var;
    b_data[i] = slope_data[i] / sqrt_var;

(虽然可能性不大, 但加上去毕竟更安全些)

[nihui]

epsilon value is handled in model converter that is pre-added to variance

[cook]

Why there is not a parameter for epsilon in the layer BatchNorm like in the layers such as InstanceNorm and MVN, I've found eps parameter in these layers. Is it inconsistency?

[nihui]

It is for some historical reason, and it is fine to add eps parameter with default value of zero for consistency.
welcome to open pull request : )