Use more placeholders in tests
dsteinberg opened this issue · comments
this is because sometimes None
or ?
dimensions are propagated in unexpected ways, especially when we have reshapes (with -1)!
A bare-bones TensorFlow framework for Bayesian deep learning and Gaussian process approximation
dsteinberg opened this issue · comments
this is because sometimes None
or ?
dimensions are propagated in unexpected ways, especially when we have reshapes (with -1)!