How should i define loss and performance metric for this CNN?

Question

I have implemented a CNN with two output layers for GTSRB Dataset problem. One output layer classifies images into their respective classes and second layer predicts bounding box coordinates. In dataset, the upper left and lower right coordinate is provided for training images. We have to predict the same for the test images. How do i define the loss metric(MSE or any other) and performance metric(R-Squared or any other) for regression layer since it outputs 4 values(x and y coordinates for upper left and lower right point)? Below is the code of model.

def get_model() :
   #Input layer
   input_layer = Input(shape=(IMG_HEIGHT, IMG_WIDTH, N_CHANNELS, ), name="input_layer", dtype='float32')
   #Convolution, maxpool and dropout layers
   conv_1 = Conv2D(filters=8, kernel_size=(3,3), activation=relu, 
            kernel_initializer=he_normal(seed=54), bias_initializer=zeros(), 
            name="first_convolutional_layer") (input_layer)
   maxpool_1 = MaxPool2D(pool_size=(2,2), name = "first_maxpool_layer")(conv_1)

   #Fully connected layers
   flat = Flatten(name="flatten_layer")(maxpool_1)
   d1 = Dense(units=64, activation=relu, kernel_initializer=he_normal(seed=45),
         bias_initializer=zeros(), name="first_dense_layer", kernel_regularizer = l2(0.001))(flat)
   d2 = Dense(units=32, activation=relu, kernel_initializer=he_normal(seed=47),
         bias_initializer=zeros(), name="second_dense_layer", kernel_regularizer = l2(0.001))(d1)

   classification = Dense(units = 43, activation=None, name="classification")(d2)
   regression = Dense(units = 4, activation = 'linear', name = "regression")(d2)
   #Model
   model = Model(inputs = input_layer, outputs = [classification, regression])
   model.summary()
   return model

score 0 · Accepted Answer · answered May 13 '20 at 11:21

0

For classification output, you need to use softmax.

classification = Dense(units = 43, activation='softmax', name="classification")(d2)

You should use categorical_crossentropy loss for the classification output.

For regression, you can use mse loss.

answered May 13 '20 at 11:21

Zabir Al Nazi

10,298
4
33
60

Like this? `model.compile(optimizer="adam", loss = {"classification" : loss, "regression" : "mse"}, metrics={"classification" : "acc"})` ? And how to get R-Squared value for regression as a metric? – Hardik Vagadia May 14 '20 at 06:34
yes, here's one implementation: https://www.kaggle.com/c/mercedes-benz-greener-manufacturing/discussion/34019 – Zabir Al Nazi May 14 '20 at 06:37
That was really helpful. Thank you. – Hardik Vagadia May 14 '20 at 14:49
Sure bro. Btw can you please also provide link to calculate weighted f1 score and micro f1 score in keras? Thank you. :) – Hardik Vagadia May 14 '20 at 15:29
You can just use https://scikit-learn.org/stable/modules/generated/sklearn.metrics.f1_score.html after getting the predictions from the model. – Zabir Al Nazi May 14 '20 at 15:35
No i mean for each epoch and validation step. I don't want to use any callbacks. How can i do that like the r2-score? – Hardik Vagadia May 14 '20 at 15:51

How should i define loss and performance metric for this CNN?

1 Answers1