fix(ops): sizes == -1 was interpreted incorrectly

[s22chan]

tf.slice does not act like tf.get_item (eg, python)

from
https://www.tensorflow.org/api_docs/python/tf/slice

If size[i] is -1, all remaining elements in dimension i are included in the slice. In other words, this is equivalent to setting:

size[i] = input_.dim_size(i) - begin[i]

this likely fixes the bfloat optimizations size issues in the TPU Inference Converter as well.

[shaobohou]

I think this is still not quite right, do you mind if I merge this one instead #220

[s22chan]

I don't see any difference other than formatting, but feel free to merge any fix. fyi:

>>> (1+0) if True else 2
1
>>> 1+0 if True else 2
1