recurrent activation function for GRU from `hard_sigmoid` to `sigmoid`, and
    `reset_after` to True in 2.0. Historically recurrent activation is
    `hard_sigmoid` since it is fast than 'sigmoid'. With new unified backend
    between CPU and GPU mode, since the CuDNN kernel is using sigmoid, we change
    the default for CPU mode to sigmoid as well. With that, the default GRU will

[]byte, e int, d, P, Q []byte) (*PrivateKey, error) { n, err := bigmod.NewModulus(N) if err != nil { return nil, err } p, err := bigmod.NewModulus(P) if err != nil { return nil, err } q, err := bigmod.NewModulus(Q) if err != nil { return nil, err } dN, err := bigmod.NewNat().SetBytes(d, n) if err != nil { return nil, err } return newPrivateKey(n, e, dN, p, q) } func newPrivateKey(n *bigmod.Modulus, e int, d *bigmod.Nat, p, q *bigmod.Modulus) (*PrivateKey, error) { pMinusOne := p.Nat().SubOne(p) pMinusOneMod,...