* update EAIS-750E compile manul

* update yolov5s_timvx example to v6.0 version

Co-authored-by: NZhiquan Wang <wangzhiquan@axera-tech.com>

* opencl add generate_cl_binary

* remove chinese cl

* add opencl cache, fix winograd limit support yolov3

* apply code-format changes

* add opencl cache, fix winograd limit support yolov3

* apply code-format changes
Co-authored-by: Nshitouren1994 <shitouren1994@users.noreply.github.com>

Bumps [github/codeql-action](https://github.com/github/codeql-action) from 1 to 2.
- [Release notes](https://github.com/github/codeql-action/releases)
- [Changelog](https://github.com/github/codeql-action/blob/main/CHANGELOG.md)
- [Commits](https://github.com/github/codeql-action/compare/v1...v2)

---
updated-dependencies:
- dependency-name: github/codeql-action
  dependency-type: direct:production
  update-type: version-update:semver-major
...
Signed-off-by: Ndependabot[bot] <support@github.com>
Co-authored-by: Ndependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

Update README.md

更新khadas最新版本timvx编译流程

* opencl add generate_cl_binary

* apply code-format changes
Co-authored-by: Nshitouren1994 <shitouren1994@users.noreply.github.com>

Bumps [codecov/codecov-action](https://github.com/codecov/codecov-action) from 2.1.0 to 3.
- [Release notes](https://github.com/codecov/codecov-action/releases)
- [Changelog](https://github.com/codecov/codecov-action/blob/master/CHANGELOG.md)
- [Commits](https://github.com/codecov/codecov-action/compare/v2.1.0...v3)

---
updated-dependencies:
- dependency-name: codecov/codecov-action
  dependency-type: direct:production
  update-type: version-update:semver-major
...
Signed-off-by: Ndependabot[bot] <support@github.com>
Co-authored-by: Ndependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* std::max_element in range [first, last)

* Comment out misleading output

* fix yolov4-tiny anchors bug

* Bump actions/cache from 2.1.7 to 3

Bumps [actions/cache](https://github.com/actions/cache) from 2.1.7 to 3.
- [Release notes](https://github.com/actions/cache/releases)
- [Commits](https://github.com/actions/cache/compare/v2.1.7...v3)

---
updated-dependencies:
- dependency-name: actions/cache
  dependency-type: direct:production
  update-type: version-update:semver-major
...
Signed-off-by: Ndependabot[bot] <support@github.com>

* apply code-format changes
Co-authored-by: Ndependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Ndependabot[bot] <dependabot[bot]@users.noreply.github.com>

Tools like `onnxsim.simplify` may convert complex subgraphs into
one node with a few `Constant` nodes in `input`,
like `Expand` and `Slice` graphs exported from PyTorch.

* std::max_element in range [first, last)

* Comment out misleading output

* std::max_element in range [first, last)

* add pytengine examples with timvx

Bumps [actions/checkout](https://github.com/actions/checkout) from 2.4.0 to 3.
- [Release notes](https://github.com/actions/checkout/releases)
- [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md)
- [Commits](https://github.com/actions/checkout/compare/v2.4.0...v3)

---
updated-dependencies:
- dependency-name: actions/checkout
  dependency-type: direct:production
  update-type: version-update:semver-major
...
Signed-off-by: Ndependabot[bot] <support@github.com>
Co-authored-by: Ndependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* read tensor data as numpy array instead of python list

this is faster by 700 times

* apply code-format changes

* read char tensor as numpy array instead of python list

* apply code-format changes

* change build sources aux

* change loop var type from @AddSalt8227
Co-authored-by: Nkalcohol <kalcohol@users.noreply.github.com>

* apply code-format changes

* fix python example error

* fix missing 'fprintf' 'stderr' problem

* fix missing <cstdlib> header problem.

* updated en doc to compile for NXP i.MX 8M Plus linux.

* adding timvx version mobilenet ssd

* updated makefile

* adding save func for operator maximum and minimum
Co-authored-by: NWang Feng <feng.wang1@hexagon.com>

* fix upsample support error

* add support for float type constant data loading

* support opset 11 version of clip op convertion

* support conv+clip fusion in graph_opt

* add asymmetric transformation mode support for resize op

* add hardswish fusion function support

* add hardswish support
Co-authored-by: Nyejunxian <yejunxian@dm-ai.com>
Co-authored-by: Nyejunxian <yejunxian@dmai.com>

* Allow cut postprocess but preserve input

* apply code-format changes
Co-authored-by: Nsunnycase <sunnycase@users.noreply.github.com>

* fix missing 'fprintf' 'stderr' problem

* fix missing <cstdlib> header problem.

* updated en doc to compile for NXP i.MX 8M Plus linux.

* adding timvx version mobilenet ssd

* updated makefile
Co-authored-by: NWang Feng <feng.wang1@hexagon.com>

* apply code-format changes

* fix bug of 'logger->prefix = prefix;'

* apply code-format changes
Co-authored-by: NRudyFoo <RudyFoo@users.noreply.github.com>

* fix missing 'fprintf' 'stderr' problem

* fix missing <cstdlib> header problem.

* updated en doc to compile for NXP i.MX 8M Plus linux.
Co-authored-by: NWang Feng <feng.wang1@hexagon.com>

update tim-vx compile version

* fix fp16 bug

* apply code-format changes
Co-authored-by: Nroot <root@ddzhao.openailab.local>
Co-authored-by: Nxiguadong <xiguadong@users.noreply.github.com>

Add cast data type casting to fix the bug `cannot convert from const char [] to char*`

* Update trt_define.h

(1) add `#include <iostream>` to fix the bug `"string" is not a member of "std"`;
(2) add `#include <string>` to fix the bug `"to_string" is not  member of "std"`;

* Update trt_executor.cc

Add cast data type casting to fix the bug `cannot convert from const char [] to char*`

* add nanodet_plus example

* apply code-format changes

* Update CMakeLists.txt
Co-authored-by: NFeiGeChuanShu <FeiGeChuanShu@users.noreply.github.com>

* fix upsample support error

* add support for float type constant data loading

* support opset 11 version of clip op convertion

* support conv+clip fusion in graph_opt
Co-authored-by: Nyejunxian <yejunxian@dm-ai.com>

fix some bugs for DFQ quantize：
（1）fix crash access node_proto.input_node_list，use `std::vector<node_graph> node_proto(graphn->node_num)` to replace `sys_malloc` when declare `node_proto`,
（2）fix declare `float ops_range[dims1]` crash，dims1 should be constant，use `float* ops_range = new float[dims1]` to repace.