TypeError: object of type 'NoneType' has no len() when using restore_best_weights=True in EarlyStopping keras

Question

I am new to using keras for deep learning applications. I am trying to perform binary classification using pre-trained models. I am running the code in google colab where the tensorflow version is 2.2.0-rc2. The following is the model I am using.

vgg19_basemodel = tf.keras.applications.VGG19(include_top = False, weights='imagenet', input_shape=(IMSIZE,IMSIZE,3))
#vgg19_basemodel.summary()

x = vgg19_basemodel.output

x = tf.keras.layers.Conv2D(16, (3,3), activation='relu')(x)
x = tf.keras.layers.MaxPooling2D(2,2)(x)
x = tf.keras.layers.Flatten()(x)
x = tf.keras.layers.Dense(32, activation="relu")(x)
x = tf.keras.layers.Dropout(0.2)(x)
x = tf.keras.layers.Dense(1, activation="sigmoid")(x)

for layer in vgg19_basemodel.layers:
  layer.trainable = False

vgg19_model = tf.keras.Model(vgg19_basemodel.input, x)
vgg19_model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=LR), loss='binary_crossentropy', metrics=['accuracy'])

#vgg19_model.summary()

The following are the callbacks I am using.

class myCallBack(tf.keras.callbacks.Callback):
  def on_epoch_end(self, epoch, logs={}):
    if(logs.get('loss') <= EXLOSS and logs.get('accuracy') >= EXACC and logs.get('val_accuracy') >= VALACC):
      print("\nCALLBAKC: TRAINING LOSS {} reached.".format(EXLOSS))
      self.model.stop_training  = True

ccall = myCallBack()

es = tf.keras.callbacks.EarlyStopping(monitor='loss', mode='min', min_delta=0.01, baseline = 0.01, patience=10, restore_best_weights=True)

I am training the model using the following:

d3_vgg19_history = vgg19_model.fit(d3_train_generator, 
                          epochs=EPOCHS,
                          validation_data=d3_test_generator, 
                          steps_per_epoch=d3_stepsize_train, 
                          validation_steps=d3_stepsize_test,
                          callbacks=[ccall, es]
                          )

The custom callback doesn't produce any problem and stops training perfectly when used without early stopping.

However, if I set the restore_best_weights=True in early stopping, the following error is generated when epoch_number == patience.

If I set restore_best_weights=False, no problems occur and training ends successfully.

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-38-f6a9ab9579ae> in <module>()
      6                           steps_per_epoch=d3_stepsize_train,
      7                           validation_steps=d3_stepsize_test,
----> 8                           callbacks=[ccall, esd3]
      9                           )

4 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py in _method_wrapper(self, *args, **kwargs)
     64   def _method_wrapper(self, *args, **kwargs):
     65     if not self._in_multi_worker_mode():  # pylint: disable=protected-access
---> 66       return method(self, *args, **kwargs)
     67 
     68     # Running inside `run_distribute_coordinator` already.

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing, **kwargs)
    811           epoch_logs.update(val_logs)
    812 
--> 813         callbacks.on_epoch_end(epoch, epoch_logs)
    814         if self.stop_training:
    815           break

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/callbacks.py in on_epoch_end(self, epoch, logs)
    363     logs = self._process_logs(logs)
    364     for callback in self.callbacks:
--> 365       callback.on_epoch_end(epoch, logs)
    366 
    367   def on_train_batch_begin(self, batch, logs=None):

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/callbacks.py in on_epoch_end(self, epoch, logs)
   1483           if self.verbose > 0:
   1484             print('Restoring model weights from the end of the best epoch.')
-> 1485           self.model.set_weights(self.best_weights)
   1486 
   1487   def on_train_end(self, logs=None):

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py in set_weights(self, weights)
   1517         expected_num_weights += 1
   1518 
-> 1519     if expected_num_weights != len(weights):
   1520       raise ValueError(
   1521           'You called `set_weights(weights)` on layer "%s" '

TypeError: object of type 'NoneType' has no len()

I have tested the early stopping in other pre-trained models, namely: vgg16, denset201, resnet, xception, inception, etc. However, the problem with the EarlyStopping persists and the same errors pop up whenever restore_best_weights is set to True. Thanks in advance for helping me out in this case. Let me know if any other information is necessary.

Answer 1

Found the "problem". It makes sense it is None because it found no better model than the baseline in my case. I got rid of "baseline=1.0" and now it works for me.