Course 3 weak 3 assignement

Course Q&A TensorFlow: Advanced Techniques Specialization Advanced Computer Vision with TensorFlow
1

I Have a problem in code I don’t know where this error comes from I successfully implemented the encoder the result exactly the same as test but the decoder gives me this error

ValueError                                Traceback (most recent call last)
<ipython-input-80-cff468b82c6a> in <module>()
      2 
      3 test_convs, test_img_input = FCN8()
----> 4 test_fcn8_decoder = fcn8_decoder(test_convs, 11)
      5 
      6 print(test_fcn8_decoder.shape)

8 frames
/usr/local/lib/python3.7/dist-packages/keras/layers/merge.py in _compute_elemwise_op_output_shape(self, shape1, shape2)
     78           raise ValueError(
     79               'Operands could not be broadcast '
---> 80               'together with shapes ' + str(shape1) + ' ' + str(shape2))
     81         output_shape.append(i)
     82     return tuple(output_shape)

ValueError: Operands could not be broadcast together with shapes (118, 182, 11) (60, 92, 11)[Copy_of_C3W3_Assignment.ipynb|attachment](upload://76mOW4r1urjvnwhCWeQwDQztHXX.ipynb) (221.2 KB)
2

Hello, husseinmleng,

the expectation is that both shapes must be same for the broadcast operation to work… can you check the code and verify the shapes of both objects?

Thank you, and good luck.

3

what are the possible solutions to fix the error? I tried several times to change the configuration of the layers and didn’t fix it