diff --git a/GPy/inference/SGD.py b/GPy/inference/SGD.py
index ca9a5a61..7cb7566f 100644
--- a/GPy/inference/SGD.py
+++ b/GPy/inference/SGD.py
@@ -257,37 +257,6 @@ class opt_SGD(Optimizer):
                 self.learning_rate = np.ones_like(self.learning_rate)*(np.dot(self.gbar_t.T, self.gbar_t) / self.hbar_t)
                 tau_t = self.tau_t*(1-self.learning_rate) + 1
 
-                # if t == 0:
-                #     N = self.model.N
-                #     Q = self.model.Q
-                #     M = self.model.M
-
-                #     iip_pos = np.arange(2*N*Q,2*N*Q+M*Q)
-                #     mu_pos = np.arange(0,N*Q)
-                #     S_pos = np.arange(N*Q,2*N*Q)
-                #     self.vbparam_dict = {'iip': [iip_pos],
-                #                          'mu': [mu_pos],
-                #                          'S': [S_pos]}
-
-                #     for k in self.vbparam_dict.keys():
-                #         hbar_t = 0.0
-                #         tau_t = 1.0
-                #         gbar_t = 0.0
-                #         self.vbparam_dict[k].append(hbar_t)
-                #         self.vbparam_dict[k].append(tau_t)
-                #         self.vbparam_dict[k].append(gbar_t)
-                # if True:
-                #     g_t = self.model.grads
-
-                #     for k in self.vbparam_dict.keys():
-                #         pos, hbar_t, tau_t, gbar_t = self.vbparam_dict[k]
-                #         gbar_t = (1-1/tau_t)*gbar_t + 1/tau_t * g_t[pos]
-                #         hbar_t = (1-1/tau_t)*hbar_t + 1/tau_t * np.dot(g_t[pos].T, g_t[pos])
-                #         self.learning_rate[pos] = (np.dot(gbar_t.T, gbar_t) / hbar_t)*1.0
-                #         tau_t = tau_t*(1-self.learning_rate[pos]) + 1
-                #         self.vbparam_dict[k] = [pos, hbar_t, tau_t, gbar_t]
-                #         print k, self.learning_rate[pos].max()
-
 
     def opt(self, f_fp=None, f=None, fp=None):
         self.x_opt = self.model._get_params_transformed()
diff --git a/GPy/models/GP.py b/GPy/models/GP.py
index b518ce4e..8f7ef9d3 100644
--- a/GPy/models/GP.py
+++ b/GPy/models/GP.py
@@ -173,7 +173,7 @@ class GP(model):
         """
         # normalize X values
         Xnew = (Xnew.copy() - self._Xmean) / self._Xstd
-        mu, var = self._raw_predict(Xnew, which_parts, full_cov)
+        mu, var = self._raw_predict(Xnew, which_parts=which_parts, full_cov=full_cov)
 
         # now push through likelihood
         mean, var, _025pm, _975pm = self.likelihood.predictive_values(mu, var, full_cov)
diff --git a/GPy/models/sparse_GP.py b/GPy/models/sparse_GP.py
index 6eb6fb49..fe9d9dc4 100644
--- a/GPy/models/sparse_GP.py
+++ b/GPy/models/sparse_GP.py
@@ -234,7 +234,7 @@ class sparse_GP(GP):
                 Kxx = self.kern.Kdiag(Xnew, which_parts=which_parts)
                 var = Kxx - np.sum(Kx * np.dot(Kmmi_LmiBLmi, Kx), 0)
         else:
-            assert which_parts=='all', "swithching out parts of variational kernels is not implemented"
+            # assert which_parts=='all', "swithching out parts of variational kernels is not implemented"
             Kx = self.kern.psi1(self.Z, Xnew, X_variance_new)#, which_parts=which_parts) TODO: which_parts
             mu = np.dot(Kx, self.Cpsi1V)
             if full_cov: