0

I am building a deeplabv3+ model but it throws a value error at the output. I am following this tutorial https://www.youtube.com/results?search_query=face+segmentation+with+deeplab3

The code is exactly the same as in that link but when I run it in Google collab, it produces the error below;

    raise ValueError(f'Output tensors of a {cls_name} model must be '
    741                          'the output of a TensorFlow `Layer` '
    742                          f'(thus holding past layer metadata). Found: {x}')

ValueError: Output tensors of a Functional model must be the output of a TensorFlow `Layer` (thus holding past layer metadata). Found: <tensorflow.python.keras.layers.convolutional.Conv2D object at 0x7f24adbeda50>

I've been stuck on this for days now and I've failed to find a solution. Someone, please help.

kana natasha
  • 47
  • 8

1 Answers1

0

The code mentioned in the above link is not showing any error when I tried replicating the same in Google colab even in different Tensorflow versions : 2.9, 2.10, 2.11 with Python 3.9.

Please try again replicating the same code in Google Colab and let us know if the issue still persists.

Attaching the replicated gist here for your reference.