CODEWITHSUNDEEP
pythonmachine-learningkerasdeep-learningcross-entropy
Edayildiz
Edayildiz

Reputation: 555

using class_weight for imbalancing data-.fit_generator()

I have imbalanced dataset with 2 classes. I am using categorical_crossentropy. I wonder about my code. Is it correct to use class_weight with categorical_crossentropy ?? If yes , does the class_weight applied only to training set or to the whole data??

I have searched many times but I didn't find any helpful sites. Any help would be appreciated.

my code:

model.compile(loss='categorical_crossentropy', optimizer=opt_adam, metrics=['accuracy'])
history=model.fit_generator(generate_arrays_for_training(indexPat, train_data, start=0,end=100)
validation_data=generate_arrays_for_training(indexPat, test_data, start=0,end=100)
steps_per_epoch=int((len(train_data)/2)), 
                                validation_steps=int((len(test_data)/2)),
                                verbose=2,class_weight = {0:1, 1:1.181},
                                epochs=65, max_queue_size=2, shuffle=True)

Upvotes: 2

Views: 278

Answers (2)

Dushi Fdz
Dushi Fdz

Reputation: 151

I do not have enough reputation to comment, but since you have asked for a reference paper, here is a newly published paper on dynamically adjusted class weights and class imbalance. https://ieeexplore.ieee.org/document/9324926

Upvotes: 1

Berkay Berabi
Berkay Berabi

Reputation: 2338

Yes, you can use the class weights with categorical cross entropy. The weights are applied when the loss function is calculated. Wrong classifications are penalized according to the weights. So the weights are applied neither to validation set nor to test set. The idea is then in training time model gives more attention to a class and updates the weights correspondingly.

That is why in the test or validation time, the learned weights will implicitly be biased with respect to class weights.

The only problem in your code might be the class weights. It can be that the weights have to add up to 1 but you should check the library details for this.

Upvotes: 1

Related Questions