TypeError: 'NoneType' object is not callable

TensorFlow General Discussion
,
1

Any idea why the following issue occured?

https://github.com/keras-team/keras/issues/17255

This happen when I try to recompile the model using callback. It should work, right?

2

Is it not valid approach (if I wanna do so)?

class CustomLearningRateScheduler(keras.callbacks.Callback):
    def on_epoch_begin(self, epoch, logs=None):
        self.model.compile(
            optimizer=keras.optimizers.RMSprop(learning_rate=0.1),
            loss="mean_squared_error",
            metrics=["mean_absolute_error"],
        )
4

Are you trying to change the learning rate of the optimizer?

maybe this could help you: Optimizers

6

Sorry for the confusion. I didn’t worry about optimizer. The above code was taken from official keras io page.

I want to recompile the keras model using callback. But I’m facing the above mentioned TypeErrror. Here is the simplified code. Please suggest.

import tensorflow as tf
from tensorflow import keras

# Define the Keras model to add callbacks to
def get_model():
    model = keras.Sequential()
    model.add(keras.layers.Dense(1, input_dim=784))
    model.compile(
        optimizer=keras.optimizers.RMSprop(learning_rate=0.1),
        loss="mean_squared_error",
        metrics=["mean_absolute_error"],
    )
    return model

# Load example MNIST data and pre-process it
(x_train, y_train), (_, _) = tf.keras.datasets.mnist.load_data()
x_train = x_train.reshape(-1, 784).astype("float32") / 255.0

class RecompileInCallback(keras.callbacks.Callback):
    def on_epoch_begin(self, epoch, logs=None):
        self.model.compile(
            optimizer=keras.optimizers.RMSprop(learning_rate=0.1),
            loss="mean_squared_error",
            metrics=["mean_absolute_error"],
        )


model = get_model()
model.fit(
    x_train,
    y_train,
    batch_size=64,
    epochs=2,
    callbacks=[
        RecompileInCallback(),
    ],
)

   1182                 _r=1):
   1183               callbacks.on_train_batch_begin(step)
-> 1184               tmp_logs = self.train_function(iterator)
   1185               if data_handler.should_sync:
   1186                 context.async_wait()

TypeError: 'NoneType' object is not callable