below is an error that many others have experienced.. I was able to mitigate the error by using a python2.7 enviroment. But google colab lately has gotten rid of py27 enviroment and its not even available in the change runtype/notebook settings options anymore to be able to choose python2/3 env: the only thing that menu has now is to specify hardware acceleration method..
Dimension 0 in both shapes must be equal, but are 800 and 533. Shapes are [800,533,3] and [533,800,3].
From merging shape 0 with other shapes. for 'stack_1' (op: 'Pack') with input shapes: [800,533,3], [533,800,3], [533,800,3].
I have tried removing some portions of code... created simple numeric variables of the image.size function (which produces the 800,533,3 tuple) and modified tf.stack to express it, and it runs longer but does eventually fail saying hat it is not receiving an expected int32/float value
below is an error that many others have experienced.. I was able to mitigate the error by using a python2.7 enviroment. But google colab lately has gotten rid of py27 enviroment and its not even available in the change runtype/notebook settings options anymore to be able to choose python2/3 env: the only thing that menu has now is to specify hardware acceleration method..
Dimension 0 in both shapes must be equal, but are 800 and 533. Shapes are [800,533,3] and [533,800,3]. From merging shape 0 with other shapes. for 'stack_1' (op: 'Pack') with input shapes: [800,533,3], [533,800,3], [533,800,3].
I have tried removing some portions of code... created simple numeric variables of the image.size function (which produces the 800,533,3 tuple) and modified tf.stack to express it, and it runs longer but does eventually fail saying hat it is not receiving an expected int32/float value