2
$\begingroup$

I have designed the following Binary Classifier Neural Network Model for a task. I want to add an early stopper to the model so that the model stops at an epoch where it has stopped learning significantly. How can I do that?

Model

X = badge1_data[['1','2','3','Score']] 
y = badge1_data['APR']

#Standardizing the Input Features
scaler = StandardScaler()
X = scaler.fit_transform(X)

#Train Test split
X_train, X_test, y_train, y_test = train_test_split(X,y, test_size=0.3)

#Create Model
model = Sequential()
model.add(Dense(4, 
                  input_dim=4, 
                  kernel_initializer='normal', 
                  activation='relu'))

model.add(Dense(2, 
                  kernel_initializer='normal', 
                  activation='relu'))
   
model.add(Dense(1, 
                  activation='sigmoid',
                  kernel_initializer='normal'))
    
#Compile Model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

#Fit Model
model.fit(X_train, y_train, epochs = 5000, validation_split = 0.3, verbose=0, batch_size=256)

#Make predictions and convert to binary value
pred_train = model.predict(X_train)
pred_test = model.predict(X_test)

#ROC AUC Score
print('Train AUC = {:}'.format(roc_auc_score(y_train,pred_train)))
print('Test AUC = {:}'.format(roc_auc_score(y_test,pred_test)))

#Accuracy
print('Train Accuracy = ',accuracy_score(y_train,pred_train.round()))
print('Test Accuracy = ',accuracy_score(y_test,pred_test.round()))
$\endgroup$
1
$\begingroup$

Early stopping can be achieved with Keras callbacks.

early_stop= tf.keras.callbacks.EarlyStopping(monitor='loss', patience=3)

history = model.fit(X, y, callbacks=[early_stop])

patience: Number of epochs with no improvement after which training will be stopped.

To define the meaning of "significant learning stopping", you will have to try with the parameters of Callback. e.g.
monitor="val_loss", min_delta=0, patience=0, mode="auto", baseline=None, etc.

Keras_API

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.