diff --git a/sklearn/pipeline.py b/sklearn/pipeline.py
index 6c98ea70efad8..348ae8df2173f 100644
--- a/sklearn/pipeline.py
+++ b/sklearn/pipeline.py
@@ -356,7 +356,7 @@ def fit_predict(self, X, y=None, **fit_params):
         Xt = X
         for name, transform in self.steps[:-1]:
             if transform is not None:
-                Xt = transform.transform(Xt)
+                Xt = transform.fit_transform(Xt)
         return self.steps[-1][-1].fit_predict(Xt, y, **fit_params)
 
     @if_delegate_has_method(delegate='_final_estimator')
diff --git a/sklearn/tests/test_pipeline.py b/sklearn/tests/test_pipeline.py
index 518c966169a28..325e9112c14cb 100644
--- a/sklearn/tests/test_pipeline.py
+++ b/sklearn/tests/test_pipeline.py
@@ -278,13 +278,20 @@ def test_fit_predict_on_pipeline():
     iris = load_iris()
     scaler = StandardScaler()
     km = KMeans(random_state=0)
+    # As pipeline doesn't clone estimators on construction,
+    # it must have its own estimators
+    scaler_for_pipeline = StandardScaler()
+    km_for_pipeline = KMeans(random_state=0)
 
     # first compute the transform and clustering step separately
     scaled = scaler.fit_transform(iris.data)
     separate_pred = km.fit_predict(scaled)
 
     # use a pipeline to do the transform and clustering in one step
-    pipe = Pipeline([('scaler', scaler), ('Kmeans', km)])
+    pipe = Pipeline([
+        ('scaler', scaler_for_pipeline),
+        ('Kmeans', km_for_pipeline)
+    ])
     pipeline_pred = pipe.fit_predict(iris.data)
 
     assert_array_almost_equal(pipeline_pred, separate_pred)