a0ae4ee2efb684a81a53a99c8e7f2689cc74e0c8,dynamicgem/embedding/dynRNN.py,DynRNN,learn_embeddings,#DynRNN#Any#,81

Before Change

        // Process inputs
        [x_hat, y] = self._autoencoder(x_in)
        // Outputs
        x_diff = merge([x_hat, x_pred],
                       mode=lambda a, b: a - b,
                       output_shape=lambda L: L[1])

        // Objectives
        def weighted_mse_x(y_true, y_pred):
            """ Hack: This fn doesn"t accept additional arguments.
                      We use y_true to pass them.
                y_pred: Contains x_hat - x_pred
                y_true: Contains b
            """
            return KBack.sum(
                KBack.square(y_pred * y_true[:, 0:self._node_num]),
                axis=-1
            )

        // Model
        self._model = Model(input=[x_in, x_pred], output=x_diff)
        sgd = SGD(lr=self._xeta, decay=1e-5, momentum=0.99, nesterov=True)
        adam = Adam(lr=self._xeta, beta_1=0.9, beta_2=0.999, epsilon=1e-08)
        self._model.compile(optimizer=adam, loss=weighted_mse_x)

After Change

        // Process inputs
        [x_hat, y] = self._autoencoder(x_in)
        // Outputs
        x_diff = Subtract()([x_hat, x_in]) 
//         x_diff = merge([x_hat, x_pred],
//                        mode=lambda a, b: a - b,
//                        output_shape=lambda L: L[1])

        // Objectives
        def weighted_mse_x(y_true, y_pred):
            """ Hack: This fn doesn"t accept additional arguments.
                      We use y_true to pass them.
                y_pred: Contains x_hat - x_pred
                y_true: Contains b
            """
            return KBack.sum(
                KBack.square(y_pred * y_true[:, 0:self._node_num]),
                axis=-1
            )

        // Model
        self._model = Model(input=[x_in, x_pred], output=x_diff)
        sgd = SGD(lr=self._xeta, decay=1e-5, momentum=0.99, nesterov=True)
        adam = Adam(lr=self._xeta, beta_1=0.9, beta_2=0.999, epsilon=1e-08)
        self._model.compile(optimizer=adam, loss=weighted_mse_x)

Instances