Is there an optimizer in keras based on precision or recall instead of loss?

Question

I am developping a segmentation neural network with only two classes, 0 and 1 (0 is the background and 1 the object that I want to find on the image). On each image, there are about 80% of 1 and 20% of 0. As you can see, the dataset is unbalanced and it makes the results wrong. My accuracy is 85% and my loss is low, but that is only because my model is good at finding the background !

I would like to base the optimizer on another metric, like precision or recall which is more usefull in this case.

Does anyone know how to implement this ?

Answer 1

You don't use precision or recall to be optimize. You just track them as valid scores to get the best weights. Do not mix loss, optimizer, metrics and other. They are not meant for the same thing.

THRESHOLD = 0.5
def precision(y_true, y_pred, threshold_shift=0.5-THRESHOLD):

    # just in case 
    y_pred = K.clip(y_pred, 0, 1)

    # shifting the prediction threshold from .5 if needed
    y_pred_bin = K.round(y_pred + threshold_shift)

    tp = K.sum(K.round(y_true * y_pred_bin)) + K.epsilon()
    fp = K.sum(K.round(K.clip(y_pred_bin - y_true, 0, 1)))

    precision = tp / (tp + fp)
    return precision


def recall(y_true, y_pred, threshold_shift=0.5-THRESHOLD):

    # just in case 
    y_pred = K.clip(y_pred, 0, 1)

    # shifting the prediction threshold from .5 if needed
    y_pred_bin = K.round(y_pred + threshold_shift)

    tp = K.sum(K.round(y_true * y_pred_bin)) + K.epsilon()
    fn = K.sum(K.round(K.clip(y_true - y_pred_bin, 0, 1)))

    recall = tp / (tp + fn)
    return recall


def fbeta(y_true, y_pred, beta = 2, threshold_shift=0.5-THRESHOLD):   
    # just in case 
    y_pred = K.clip(y_pred, 0, 1)

    # shifting the prediction threshold from .5 if needed
    y_pred_bin = K.round(y_pred + threshold_shift)

    tp = K.sum(K.round(y_true * y_pred_bin)) + K.epsilon()
    fp = K.sum(K.round(K.clip(y_pred_bin - y_true, 0, 1)))
    fn = K.sum(K.round(K.clip(y_true - y_pred, 0, 1)))

    precision = tp / (tp + fp)
    recall = tp / (tp + fn)

    beta_squared = beta ** 2
    return (beta_squared + 1) * (precision * recall) / (beta_squared * precision + recall) 


def model_fit(X,y,X_test,y_test):
    class_weight={
    1: 1/(np.sum(y) / len(y)),
    0:1}
    np.random.seed(47)
    model = Sequential()
    model.add(Dense(1000, input_shape=(X.shape[1],)))
    model.add(Activation('relu'))
    model.add(Dropout(0.35))
    model.add(Dense(500))
    model.add(Activation('relu'))
    model.add(Dropout(0.35))
    model.add(Dense(250))
    model.add(Activation('relu'))
    model.add(Dropout(0.35))
    model.add(Dense(1))
    model.add(Activation('sigmoid'))

    model.compile(loss='binary_crossentropy', optimizer='adamax',metrics=[fbeta,precision,recall])
    model.fit(X, y,validation_data=(X_test,y_test), epochs=200, batch_size=50, verbose=2,class_weight = class_weight)
    return model