AttributeError: 'CyclicLR' object has no attribute 'on_train_batch_begin'

[Serge3006]

Hi, I've tried to use your class within my training code, but I got the following error: AttributeError: 'CyclicLR' object has no attribute 'on_train_batch_begin'.

My code is the following:

from tensorflow.keras.applications.resnet50 import ResNet50

base_model = ResNet50(weights='imagenet', include_top=False)
base_model.trainable = False

model = tf.keras.Sequential([
base_model,
tf.keras.layers.GlobalAveragePooling2D(),
tf.keras.layers.Dense(units=200, activation='relu'),
tf.keras.layers.Dense(units=5, activation="softmax")
])

model.compile(optimizer=tf.keras.optimizers.Adam(0.001), metrics=["accuracy"],
loss=tf.keras.losses.sparse_categorical_crossentropy)
clr = CyclicLR(base_lr=0.001, max_lr=0.006, step_size=240)
model.fit(train_dataset, epochs=30, steps_per_epoch=60, validation_data=val_dataset,
validation_steps=1, callbacks=[clr])

By the way train_dataset and val_dataset are tf.data.Datasets.

Versions: Python3 and TF 1.10.

Any idea why the issue?

[Rendiere]

Hey, I've had a similar issue and I think it's because the tensorflow port of Keras has a slightly different callback API than the original Keras.

To fix this, just replace everywhere you use tf.keras with keras and be sure to import keras (not tensorflow.keras!) in your script.

Let me know if this worked :D