LSTMのモデルでGridsearchCVを使用したところTypeError: If no scoring is specifiedのエラーが出る

Question

LSTMのハイパパラメータをグリッドサーチによって調整したいです。
しかしcodeを実行すると以下のエラー文が出てしまいます。

def grid(df,length_of_sequences):
    (X_train, y_train), (X_test, y_test) = train_test_split(df,test_size=0.2,n_prev=length_of_sequences)
    out_neurons = 1
    in_neurons=len(df.columns)
    hidden_neurons = 300
    model = Sequential()
    model.add(LSTM(hidden_neurons, batch_input_shape=(None, length_of_sequences, in_neurons), kernel_initializer = glorot_uniform(seed=20201119),return_sequences=False))
    model.add(Dense(out_neurons))
    model.add(Activation("linear"))
    model.compile(loss="mean_squared_error", optimizer="adam",)
    #グリッドサーチ対象のハイパーパラメーターを準備
    activation = ["linear","relu", "sigmoid"]
    optimizer = ["adam", "adagrad"]
    batch_size = [32, 64,128]
    
    #グリッドサーチ対象のハイパーパラメーターを辞書型にまとめる
    param_grid = dict(activation=activation, optimizer=optimizer, batch_size=batch_size)
    
    #グリッドサーチの実行
    grid = GridSearchCV(estimator=model, param_grid=param_grid)
    scores = 'precision'#['precision', 'recall']
    grid_result = grid.fit(X_train, y_train,scoring="accuracy")
    return grid_result

    116     grid = GridSearchCV(estimator=model, param_grid=param_grid)
    117     scores = 'precision'#['precision', 'recall']
--> 118     grid_result = grid.fit(X_train, y_train,scoring="accuracy")
    119     return grid_result
    120 

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/sklearn/model_selection/_search.py in fit(self, X, y, groups, **fit_params)
    593 
    594         scorers, self.multimetric_ = _check_multimetric_scoring(
--> 595             self.estimator, scoring=self.scoring)
    596 
    597         if self.multimetric_:

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/sklearn/metrics/scorer.py in _check_multimetric_scoring(estimator, scoring)
    340     if callable(scoring) or scoring is None or isinstance(scoring,
    341                                                           six.string_types):
--> 342         scorers = {"score": check_scoring(estimator, scoring=scoring)}
    343         return scorers, False
    344     else:

/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/sklearn/metrics/scorer.py in check_scoring(estimator, scoring, allow_none)
    297                 "If no scoring is specified, the estimator passed should "
    298                 "have a 'score' method. The estimator %r does not."
--> 299                 % estimator)
    300     else:
    301         raise ValueError("scoring value should either be a callable, string or"

TypeError: If no scoring is specified, the estimator passed should have a 'score' method. The estimator <keras.engine.sequential.Sequential object at 0x2225b1b00> does not.

評価方法は

grid_result = grid.fit(X_train, y_train,scoring="accuracy")

にてaccuracyを指定しているはずなのですがエラーが出てしまいます。
原因が調べても分からなかったためどなたか知恵をお貸しいただけると幸いです。