Hot to fix Tensorflow model not running in Eager mode with .fit()?

Question

I'm trying to run a basic CNN keras model in Eager Execution but Tensorflow refuses to treat the model as eager. I originally attempted this in stable 1.13 branch (latest), making sure to enable eager execution with no result. I upgraded to 2.0 (latest) but again nothing.

Model

class CNN2(tf.keras.Model):
  
  def __init__(self, num_classes=7):
    super(CNN2, self).__init__()
    self.cnn1 = tf.keras.layers.Conv2D(32, (5,5), padding='same', strides=(2, 2),
                                      kernel_initializer='he_normal')
    self.bn1 = tf.keras.layers.BatchNormalization()
    self.cnn2 = tf.keras.layers.Conv2D(64, (5,5), padding='same', strides=(2, 2),
                                      kernel_initializer='he_normal')
    self.cnn3 = tf.keras.layers.Conv2D(128, (5,5), padding='same', strides=(2, 2),
                                      kernel_initializer='he_normal')
    self.bn2 = tf.keras.layers.BatchNormalization()
    self.pool = tf.keras.layers.MaxPooling2D((2,2))
    self.dnn1 = tf.keras.layers.Dense(128)
    self.dropout1 = tf.keras.layers.Dropout(0.45)
    self.flatten = tf.keras.layers.Flatten()
    self.dnn2 = tf.keras.layers.Dense(512)
    self.dnn3 = tf.keras.layers.Dense(256)
    self.classifier = tf.keras.layers.Dense(num_classes)    

  def simpleLoop(self, inputs, x):
        #x_Numpy = x.numpy(),
        for i, input in inputs:
            print("{0} - {1}".format(i,len(input)))             
    
  def call(self, inputs, training=None, mask=None):
    print(tf.executing_eagerly())
    x = tf.nn.leaky_relu(self.cnn1(inputs))
    x = self.bn1(x)
    x = self.pool(x)
    x = tf.nn.leaky_relu(x)
    x = tf.nn.leaky_relu(self.bn2(self.cnn2(x)))
    x = self.pool(x)
    x = self.dropout1(tf.nn.leaky_relu(self.cnn3(x)))
    x = self.flatten(x)
    self.simpleLoop(inputs, x)
    x = self.dropout1(self.dnn1(x))
    x = self.dropout1(self.dnn2(x))
    x = self.dropout1(self.dnn3(x))
    output = self.classifier(x)
    
    #with tf.device('/cpu:0'):
    output = tf.nn.softmax(output)
      
    return output

Parameter Setting

batch_size = 50
epochs = 150
num_classes = 7

Checking Eager is on and version

print(tf.executing_eagerly())
print(tf.__version__)
>>True
>>2.0.0-alpha0

Running the Model

modelE = CNN2(num_classes)
modelE.run_eagerly = True
print(modelE.run_eagerly)


#model = CNN2(num_classes)
modelE.compile(optimizer=tf.optimizers.Adam(0.00008), loss='categorical_crossentropy', 
              metrics=['accuracy'], run_eagerly=True)

# TF Keras tries to use entire dataset to determine shape without this step when using .fit()
# Fix = Use exactly one sample from the provided input dataset to determine input/output shape/s for the model
dummy_x = tf.zeros((1, size, size, 1))
modelE._set_inputs(dummy_x)

# Train
hist = modelE.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, 
          validation_data=(x_test, y_test), verbose=1)

# Evaluate on test set
scores = modelE.evaluate(x_test, y_test, batch_size, verbose=1)

This results in the error AttributeError: 'Tensor' object has no attribute 'numpy'

And when I remove the offending line x.numpy() I instead get this error TypeError: Tensor objects are only iterable when eager execution is enabled. To iterate over this tensor use tf.map_fn.

It also prints False for the print(tf.executing_eagerly()) located within the def call() method of the model.

---

How can it be forced into eager mode and not a graph? Again I tried this in both up to date 1.13 and 2.0. Is this a bug?

Solution

It took a while to find a solution that works for me in tensorflow==2.0.0, so I wanted to share it here in case it helps other people too:

model.compile(run_eagerly=True)

If that doesn't work, you can try to force it after the model compiles:

model.compile()
model.run_eagerly = True