Adopt the "set -u" idiom from the docker scripts as a mechanism to
improve future robustness.

* Fix Relay ARM CPU spatial pack depthwise alter op layout issue.

* Update tune_relay_arm.py

A number of test scripts use the '|| exit 1' idiom.  This has two
issues, first process exit codes are defined to be in the range 0-255.
Second, more importantly, the idiom is fragile because it requires
that every possible failure point be explicitly coded.  This patch
removes the idiom in favour of "set -e" as used in the docker scripts
as a more robust mechanism to ensure that script failures are always
caught and propagated by default.

* Add dense schedules to __init__ for cpu

* Add documentation for topi::shape

* Add additional imports to topi CPU __init__.

* [Relay][Op] Add group conv2d dispatch to topi function

* Rerun tests

* decompile tf control flow

* Add docs

* remove import relay

* move tests under tensorflow frontend

* minor fix

* Fix error reporting for missing axis

* Update data_layout.cc

* improved `multiply_rewrite` for gluoncv_ssd quantization

* add a check to attach_simulated_quantize below to prevent quantizing lhs to INPUT if lhs_kind is INPUT;

The dict which is used to initilize OrderDict is not ordered, so
  metadata may not be at the end.

* Add ops in mxnet converter

* trigger ci

* [AlterLayout] NCHW upsampling

* [Relay][Pass] Fix Depthwise AlterLayout

* [Relay][Frontend][keras] added interpolation method of Upsampling2D.

* added testcase

* small fixes

* [FRONTEND][TENSORFLOW] Enhance with left over patches from NNVM.

commit 76188a43
Author: Siva sivar.b@huawei.com
[NNVM][TENSORFLOW] bugfix. (#2444)

commit 6737739c
Author: Ashutosh Parkhi ashutosh.parkhi@imgtec.com
[Tensorflow] Support for Crop (#2285)

commit f6c3f997
Author: Alexey Romanov alexey.v.romanov@gmail.com
[FRONTEND][TENSORFLOW] Use input shapes directly instead of 1-element lists (#2242)

commit e5d92e1b
Author: Dominic Symes 36929632+dominicsymes@users.noreply.github.com
[FRONTEND][TENSORFLOW] Bugfix (#2326)

commit 00d509d4
Author: Alexey Romanov alexey.v.romanov@gmail.com
[FRONTEND][TENSORFLOW] Support Unstack and Split (#2105)

commit df9d3ad2
Author: Siva sivar.b@huawei.com
[FRONTEND][TENSORFLOW] Bugfix (#2267)

commit d1a0c901
Author: Zhebin Jin zhebin.jzb@alibaba-inc.com
[FRONTEND][TENSORFLOW]Add Split and realdiv op support (#2123)
* Add Split and realdiv op support
* Fix the pad calculation in the case of dilated convolution

* 	* review comments

* 	* resnet fix.

* 	* review comments

This patch reverts one of my earlier patches (squashed in #2710) to
reduce bandwidth requirements of git clone, in this particular case we
are checking out a specific hash rather than a tag or branch name. The
--branch option to git clone permits tags or branches but does not
permit a specific hash.

Code like this can't be built with NV OpenCL, and it needs an explicit type
  converison for ternary expression if return type is uchar.

       uchar i = 0, j = 0;
       uchar t = max((uchar)j, ((i > 0) ? (uchar)1 : (uchar)0));