Image_segmentation_Unet_v2 Output tensors of a Functional model must be the output of a TensorFlow `Layer`

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

I did everything with already imported modules in conv_block(inputs=None, n_filters=32, dropout_prob=0, max_pooling=True) but I get enough strange error

ValueError: Output tensors of a Functional model must be the output of a TensorFlow Layer (thus holding past layer metadata). Found: <keras.layers.pooling.max_pooling2d.MaxPooling2D object at 0x7fe38c462100>

2

Please read functional api to understand that 2 steps are involved in creating a model using functional api.

  1. Create a layer
  2. Invoke the __call__ function of the layer with the correct parameter.
3

oh, indeed, I should call tf.func()(conv) additionally. Thx