Are the equivalent class of split extension of $G$ by $K$ really in one to one correspondence with homomorphisms $G \to \mathrm{Aut}(K)$?
When I am trying to prove it, I find it may be not the case.
I only know that 
$$1\to K\to K\rtimes_{\rho_1}G\to G\to 1 \quad\text{and}\quad 1\to K\to K\rtimes_{\rho_2}G\to G\to 1$$ 

are equivalent if and only if there is a nonabelian 1-cocycle $\beta:G\to K$ such that $\rho_1=\mathrm{Ad}_{\beta}\circ \rho_2$. When $\rho_1=\rho_2$, $\beta$ is an abelian 1-cocycle. Thus, the automrophism group of $1\to K\to K\rtimes_{\rho}G\to G\to 1$is isomorphic to $Z^{1}_{\rho}(G,C_K)$.