4

I am fitting a model using keras and passed the callbacks list to the model fit_generator but encounterd the following error.Please help.

AttributeError: 'function' object has no attribute 'set_model'

Code snippet :

    from keras.callbacks import LearningRateScheduler
    import numpy as np
    from keras import optimizers
    from keras.callbacks import *

    def lr_schedule(epoch):
        lrate = 0.1
        if epoch > 50:
            lrate = 0.01
        elif epoch > 75:
            lrate = 0.001       
        return lrate


    filepath="latest_weight_ckpt_{epoch:02d}_{val_acc:.2f}.hdf5"
    model_ckpt = ModelCheckpoint(filepath, monitor='val_acc', verbose=1, 
    save_best_only=True, mode='max')
    #lists = [model_ckpt]


    #model_checkpoint= ModelCheckpoint("weights/DenseNet-BC-100-12- 
    CIFAR100.h5", monitor="val_acc", 
    save_best_only=True,save_weights_only=True)

    callbacks_list=[lr_schedule, model_ckpt]

    model.fit_generator(train_generator, epochs=25, 
    steps_per_epoch=200,verbose=1, validation_steps=200, 
    validation_data=validation_generator,callbacks=callbacks_list)

1 Answer 1

6

The problem is that you are passing a python function (lr_schedule) as a callback instead of a Keras callback object. You should instead use the Keras LearningRateScheduler callback as follows:

lr = LearningRateScheduler(lr_schedule)
callbacks_list=[lr, model_ckpt]
Sign up to request clarification or add additional context in comments.

Comments

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.