* [LICENSE] add 3rdparty licenses

* rename license files to .txt

* [Golang][Doc] improve the samples and doc

* [Golang][Doc] add asf header

* [Golang][Doc] Improve the end to end example

* [Golang][Doc] Improve the end to end example

* [VM] add a few more API to vm

* [VM][Fix] fix vm convert args

* [VM] a few fixes

* rename fields

* update

* update vm profiler

* x

* add doc

* lint

* fix test

* address comments

* [TOPI] Fix flaky testcase for floor div

* avoid check at 0.0

* fix slice bug when input is param

* use _infer_value rather than _infer_value_simulated

Previously, we would rely on the later phases to error out
(often for using too much shared memory). This enables the
checks on the IR that already exist for CUDA and OpenCL also
for ROCm.

* [ThreadPool] Solve thread transitions issue

* Use pthread_atfork to avoid master thread affinity be derived by child.

* Code Format

* comment of exclude_worker0_

* set full cpu affinity

* Redundant blank line

* CPPLint

* CPPLint namespace

* CPPLint

* Fix the wrong logic of bind master thread.

* [Relay][Quantize] Integrate data-aware calibration into quantization

* Update _calibrate.py

* trigger ci

* Address comments

* address comments

* [PERF] parallel reduction in cpu

* fix

* x

* update

* lint

* fix

* [tutorial] nnvm -> relay

* use relay workload

* delete movbilenetv2 option

* add rule for clean

* Update clean rule

Seems like lib/ directory is not made by the makefile
So don't delete directory, just the contents of it.

* Add tf FloorMod

* Add floor_div/mod into topi and relay

* Add to rst

* Fix test

* [Relay][Frontend][Tensorflow]Add conv2d_transpose

* add transformation from NHWC to NCHW to compatible with TVM conv2d_transpose implementation

* remove 'dilations' paramater to compitable with TF1.3

When getting cuda schedule passing single tensor seem to work but after changing target to "llvm" causes assert.
Sending list on other hand makes both cuda and llvm targets happy.
See https://discuss.tvm.ai/t/solved-simple-example-error-attributeerror-tensorslice-object-has-no-attribute-op/2245/3

* Add qnn conv2d attributes for input_tensor_scale and
kernel_tensor_scale.

The lowering in the tflite frontend loses the input_tensor_scale
and the kernel_tensor_scale by multiplying it and putting it into
the Requantize operation. This means that any graph partitioning
passes or other passes that need to access this information no longer
have it available in the qnn dialect.

regards
Ramana

* Store input tensor scale and Weight tensor scale for Dense as well

As for conv2d, the tflite frontend drops the input tensor
scale and the weight tensor scale from the relay op. Store
it as separate fields in there.

* Fix unintentional tab

* Rename input_tensor_scale to input_scale and kernel_tensor_scale
to kernel_scale for conv2d.

* input_tensor_scale -> input_scale weight_tensor_scale->weight_scale

* Rework dense testcase

And use input_scale and kernel_scale

* Be consistent in use of input_scale and kernel_scale values

* Fixup qnn conv2d tests for input_scale and kernel_scale

* Make pydoc identical between conv2d and dense for weight_tensor

* Fix up conv2d parameters to be in the same order between C++ and python

* Fix ordering of parameters for dense.

* Add input_scale and output_scale to try and satisfy ci gods

* Delete input_scale and kernel_scale.

nn.conv2d does not contain input_scale and kernel_scale. We need
to delete it when lowering it to nn.conv2d.

* Add input_scale and kernel_scale for qnn.conv2d