[FIXED] Early stopping does not work in my code in keras with TensorFlow

Issue

When I am using early stopping the model trains for one epoch only, which is not what should be doing.

Here is the example without early stopping:

# split a univariate sequence into samples

def split_sequence(sequence, n_steps):
    X, y = list(), list()
    for i in range(len(sequence)):
        # find the end of this pattern
        end_ix = i + n_steps
        # check if we are beyond the sequence
        if end_ix > len(sequence)-1:
            break
        # gather input and output parts of the pattern
        seq_x, seq_y = sequence[i:end_ix], sequence[end_ix]
        X.append(seq_x)
        y.append(seq_y)
    return np.array(X), np.array(y)

sequence = np.arange(10, 1000, 10)

n_steps = 3

X, y = split_sequence(sequence, n_steps)

n_features = 1
X = X.reshape((X.shape[0], X.shape[1], n_features))

model = Sequential()
model.add(LSTM(50, activation='relu', input_shape=(n_steps, n_features)))
model.add(Dense(1))
model.compile(optimizer='adam', loss='mean_absolute_percentage_error')


# early_stopping = EarlyStopping(monitor='val_loss', patience= 5)

hist = model.fit(X, y, validation_split=0.2,  batch_size = 16, epochs = 200)

As can be seen in the following screenshots the error is continuously declining for the first 15+ epochs:

Now if I try early stopping it stops in the first epoch:

hist = model.fit(X, y, validation_split=0.2,  callbacks = [EarlyStopping(patience=5)], batch_size = 16)

What I am doing wrong and how can I correct it?

Solution

You forgot to specify the number of epochs in this call, so it defaults to 1:

hist = model.fit(X, y, validation_split=0.2,  callbacks = [EarlyStopping(patience=5)], batch_size = 16)

Change it to:

hist = model.fit(X, y, validation_split=0.2,  callbacks=[EarlyStopping(patience=5)], batch_size=16, epochs=200)

Cheers

Answered By - Daniele Grattarola