Apple M1 上的 Keras

Question

I am running following command on my Apple M1 system.

----------Code Start----------------------

from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D, Dropout, Flatten, Dense, Activation, BatchNormalization

model = Sequential()

model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(IMAGE_WIDTH, IMAGE_HEIGHT, IMAGE_CHANNELS)))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Conv2D(128, (3, 3), activation='relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(512, activation='relu'))
model.add(BatchNormalization())
model.add(Dropout(0.5))
model.add(Dense(2, activation='softmax')) # 2 because we have cat and dog classes

model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])

model.summary()

FAST_RUN = True
epochs=3 if FAST_RUN else 50

history = model.fit_generator(
    train_generator, 
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps=size_test//batch_size,
    steps_per_epoch=size_train//batch_size,
    callbacks=callbacks
)

---------------Code End------------------

It is giving me the following error which i am not able to figure out.

---------------Error Start---------------------

1157               callbacks.on_train_batch_begin(step)
-> 1158               tmp_logs = self.train_function(iterator)
   1159               if data_handler.should_sync:
   1160                 context.async_wait()

~/miniforge3/envs/tensorflow/lib/python3.9/site-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
    887 
    888       with OptionalXlaContext(self._jit_compile):
--> 889         result = self._call(*args, **kwds)
    890 
    891       new_tracing_count = self.experimental_get_tracing_count()

~/miniforge3/envs/tensorflow/lib/python3.9/site-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
    915       # In this case we have created variables on the first call, so we run the
    916       # defunned version which is guaranteed to never create variables.
--> 917       return self._stateless_fn(*args, **kwds)  # pylint: disable=not-callable
    918     elif self._stateful_fn is not None:
    919       # Release the lock early so that multiple threads can perform the call

TypeError: 'NoneType' object is not callable

--------------Error End-----------------

What should I do to resolve this?

Answer 1

You need to do some changes in both these lines below as you said it is category 2 binary_class model (0,1).

model.add(Dense(1, activation='sigmoid')) # 2 because we have cat and dog classes
model.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])

Also try changing these below codes because steps_per_epoch and validation_steps are not counting correctly. You can check this link for more information in this.

history = model.fit(
    train_generator, 
    epochs=epochs,
    validation_data=validation_generator)
    #validation_steps=size_test//batch_size,
    #steps_per_epoch=size_train//batch_size)

Let us know if issue still persists.