Enable test case for float64 with conv1d (#19179)

The float64 for conv2d support has been added to tensorflow
in e3468b56. (Thanks brianwa84!)
Since conv1d implementation invokes conv2d, the float64 support
for conv1d is supported now as well.

This fix adds the test case for float64 support of conv1d and
removes the TODO.

This fix fixes 19175.

Signed-off-by: Yong Tang <yong.tang.github@outlook.com>