y_true and y_pred have different number of output (10!=1)

I am using Scikit learn wrapper KerasClassifier for hyperparameters tuning for my LSTM model using RandomizedSearchCV. Below is a summary of what I am doing: 1. xtrain has the shape [355,5,10] and ytrain has the shape[355,10], There are 355 training samples and 10 features and labels. 2. First I create the model using build_lstm_model function 3. Define KerasClassifier 4. Specify parameters that to be sued for fitting to determine the scoring 5. Specify parameters to be searched using RandomizedSearchCV 5. fit the model

I am using 'neg_mean_squared_error' as the scoring metrics. When I run the code I get an error "y_true and y_pred have different number of output (10!=1)"

I found that, if I do not specify any scoring metrics, then it works fine. But, I want to use neg_mean_squared_error, since its a regression problem.

# keras model
def build_lstm_model(n_blocks=6, n_cells=40, lr=0.001, lookback=lookback, n=n): model = Sequential() for i in range(n_blocks-1): model.add(LSTM(n_cells, input_shape=(lookback, n), return_sequences=True, activation='tanh', kernel_initializer='uniform')) model.add(LSTM(n_cells, input_shape=(lookback, n), activation='tanh', kernel_initializer='uniform')) model.add(Dense(n)) adam = optimizers.Adam(lr=lr, beta_1=0.9, beta_2=0.999, epsilon=None, decay=0.0, amsgrad=False) model.compile(loss='mean_squared_error', optimizer=adam, metrics=['accuracy']) return model
# pass in fixed parameters n_input and n_class
model_lstm = KerasClassifier( build_fn = build_lstm_model, lookback = lookback, n = n)
# specify other extra parameters pass to the .fit
# number of epochs is set to a large number
keras_fit_params = { 'epochs': 10, 'batch_size': 16, 'validation_data': (xvalid, yvalid), 'verbose': 0
}
# random search parameters
# specify the options and store them inside the dictionary
# batch size and training method can also be hyperparameters, but it is fixed
n_blocks_params = [3, 4, 5, 6, 7, 8]
n_cells_params = [20, 30, 40, 50, 60]
lr_params = [0.001, 0.0001]
keras_param_options = { 'n_blocks': n_blocks_params, 'n_cells': n_cells_params, 'lr': lr_params
}
# `verbose` 2 will print the class info for every cross-validation, kind of too much
rs_lstm = GridSearchCV( model_lstm, param_distributions = keras_param_options, #fit_params = keras_fit_params, scoring = 'neg_mean_squared_error', n_iter = 3, cv = 5, n_jobs = -1 #verbose = 0
)
rs_lstm.fit(xtrain, ytrain)

Is there a way I can use mean_squared_error as the metrics in RandomizedSearchCV?

1 Answer

I was using KerasClassifier. I didn't know that there is another wrapper KerasRegressor in SKlearn. When I use KerasRegressor, I can use regression related metrics for finding a good model. Thank you.