* Support TFLite FP32 Relay frontend.

* Fix lint issue

* Remove unnecessary variables and packages

* Add method doc string

* Fix capital letter of method doc string

* Add TFLite FP32 Relay frontend based on latest code

* Merge the latest code

* Solve cython issue with relay type inference

* Modify code based on suggestions

* use IPV6 instead of IPV4

* backward compatible

* add error report

* fix linter

* more linter

* fix the python2 api

* Avoid runtime exception when file doesn't exist

* Update the check based on feedback

* Revert the old fix

* [RELAY][PASS] Support Negative Scale in FoldScaleAxis

* Fix comment

* [Doc][Tutorial] Add the instructions how to use contrib_spatial_pack

* Update the code according suggestions

* on the way to enable hybrid schedule

* I think I am done with imperfect loop split?

* copyright watermark

* loop annotation

* fix lint

* fix lint 1

* shit!

* loop reorder supported

* support bind to add some tests

* fused tested

* imperfect loop testcase

* fix lint

* add bind testcase

* fix doc

* fix online edit typo

* resolve @mercymercy review

* fix indent

* i should convince myself it is not flaky test first

* fix test hybrid

* how many flaky test are you expecting; i ball ball u to let me pass

* rebase halide...

* init

staging on

final save before staging

save

init ver

init ver

ll stuff

save

add failing test

add file

pass test

fix error

huh?

save

Add test changes

Fix fusion with nested tuples

Fix reverse mode test

More hacking

Clean up AD

Hacking on reverse mode

Fix issue in reverse

save

fix lint

fix lint

fix lint

save

save

fix

support neg

address some comment

add back file

save

save

* save

* save

* save

* lint

* fix lint

* save

* fix

fixes

fixes

* Add GEMM autotvm template for x86

* Fix tophub link

* Disable RPC server logging file delete

* Update dense autotvm template

* Fix tests

* Fix lint

* tweak

* Register two templates with different tags

* Remove duplicated frontend tests

* Add test for nnvm to relay

* Add test to script

* Remove dcgan in nnvm_to_relay test due to unsupported op in cuda

* Fix bug in converting conv2d from nnvm to relay

* Fix dropout