CODEWITHSUNDEEP
python-3.xkerastensorflow2.0
seni
seni

Reputation: 711

TypeError: Expected tensorflow.python.keras.engine.training.Model, found tensorflow.python.framework.ops.Tensor

I would like to write a Resnet 18 model, so I found this code, knowing that my dataset is an image dataset and my labels are 2 (num_classes=2), I find this error that I can't understand it. Here is my model :

def create_compiled_keras_model():    

    inputs = tf.keras.Input((224, 224, 3))
    regularizer = None

    x = tf.keras.layers.ZeroPadding2D(padding=(3,3), name='pad')(inputs)
    x = tf.keras.layers.Conv2D(filters=64, kernel_size=7, strides=2, padding='valid', activation='linear', 
                               use_bias=False, kernel_initializer='he_normal', kernel_regularizer=regularizer, name='conv1')(x)
    x = tf.keras.layers.BatchNormalization(momentum=0.1, epsilon=1e-5, name='bn1')(x)
    x = tf.keras.layers.Activation('relu', name='relu')(x)
    x = tf.keras.layers.ZeroPadding2D(padding=(1,1), name='pad1')(x)
    x = tf.keras.layers.MaxPool2D(pool_size=3, strides=2, padding='valid', name='maxpool')(x)

    x = BasicBlock(x, num_channels=64, kernel_size=3, num_blocks=2, skip_blocks=[], regularizer=regularizer, name='layer1')

    x = BasicBlockDown(x, num_channels=128, kernel_size=3, regularizer=regularizer, name='layer2')
    x = BasicBlock(x, num_channels=128, kernel_size=3, num_blocks=2, skip_blocks=[0], regularizer=regularizer, name='layer2')

    x = BasicBlockDown(x, num_channels=256, kernel_size=3, regularizer=regularizer, name='layer3')
    x = BasicBlock(x, num_channels=256, kernel_size=3, num_blocks=2, skip_blocks=[0], regularizer=regularizer, name='layer3')

    x = BasicBlockDown(x, num_channels=512, kernel_size=3, regularizer=regularizer, name='layer4')
    x = BasicBlock(x, num_channels=512, kernel_size=3, num_blocks=2, skip_blocks=[0], regularizer=regularizer, name='layer4')

    x = tf.keras.layers.GlobalAveragePooling2D(name='avgpool')(x)
    x = tf.keras.layers.Dense(units=1000, use_bias=True, activation='linear', kernel_regularizer=regularizer, name='fc')(x)
    #x = tf.keras.layers.GlobalAveragePooling2D()(x)
    #x = tf.keras.layers.Dense(units=2, use_bias=False, name='output', activation='relu')(x)
  
    model_output = tf.keras.layers.Dense(units=2,use_bias=False, name='output', activation='relu')(x)
    model = tf.keras.Model(inputs, model_output)
    model.compile(optimizer=tf.keras.optimizers.SGD(learning_rate=0.001), 
             loss=tf.keras.losses.CategoricalCrossentropy(),
              metrics=[tf.keras.metrics.CategoricalAccuracy()])
    return x

Error: TypeError: Expected tensorflow.python.keras.engine.training.Model, found tensorflow.python.framework.ops.Tensor.

Upvotes: 0

Views: 451

Answers (1)

ashraful16
ashraful16

Reputation: 2782

You are returning the wrong variable. I think you should return model instead of x.

Upvotes: 2

Related Questions