mvivarelli

def weighted_categorical_crossentropy(weights):

    weights = K.variable(weights)
        
    def loss(y_true, y_pred):
        # scale predictions so that the class probas of each sample sum to 1
        y_pred /= K.sum(y_pred, axis=-1, keepdims=True)
        # clip to prevent NaN's and Inf's
        y_pred = K.clip(y_pred, K.epsilon(), 1 - K.epsilon())
        # calc

mvivarelli

#model
model = Sequential()
#input
model.add(LSTM(units=50, return_sequences=True, activation='tanh', batch_size=batch_size, stateful=True, input_shape = (x_train_final.shape[1], x_train_final.shape[2])))
model.add(Dropout(0.2))
#hidden layer 1
model.add(LSTM(units=60, return_sequences=True, activation='tanh', stateful=True))
model.add(Dropout(0.2))
#hidden layer 2
model.add(LSTM(units=60, return_sequences=True, activation='tanh', stateful=True))