Commit Graph

11 Commits

Author SHA1 Message Date
llh721113
a30c987f87 feat: RVP052 Optimization for DNN int8layers 2023-12-21 14:51:41 +08:00
Liutong HAN
a287605c3e Clean up the Universal Intrinsic API. 2023-10-13 19:23:30 +08:00
HAN Liutong
07bf9cb013
Merge pull request #24325 from hanliutong:rewrite
Rewrite Universal Intrinsic code: float related part #24325

The goal of this series of PRs is to modify the SIMD code blocks guarded by CV_SIMD macro: rewrite them by using the new Universal Intrinsic API.

The series of PRs is listed below:
#23885 First patch, an example
#23980 Core module
#24058 ImgProc module, part 1
#24132 ImgProc module, part 2
#24166 ImgProc module, part 3
#24301 Features2d and calib3d module
#24324 Gapi module

This patch (hopefully) is the last one in the series. 

This patch mainly involves 3 parts
1. Add some modifications related to float (CV_SIMD_64F)
2. Use `#if (CV_SIMD || CV_SIMD_SCALABLE)` instead of `#if CV_SIMD || CV_SIMD_SCALABLE`, 
    then we can get the `CV_SIMD` module that is not enabled for `CV_SIMD_SCALABLE` by looking for `if CV_SIMD`
3. Summary of `CV_SIMD` blocks that remains unmodified: Updated comments
    - Some blocks will cause test fail when enable for RVV, marked as `TODO: enable for CV_SIMD_SCALABLE, ....`
    - Some blocks can not be rewrited directly. (Not commented in the source code, just listed here)
      - ./modules/core/src/mathfuncs_core.simd.hpp (Vector type wrapped in class/struct)
      - ./modules/imgproc/src/color_lab.cpp (Array of vector type)
      - ./modules/imgproc/src/color_rgb.simd.hpp (Array of vector type)
      - ./modules/imgproc/src/sumpixels.simd.hpp (fixed length algorithm, strongly ralated with `CV_SIMD_WIDTH`)
      These algorithms will need to be redesigned to accommodate scalable backends.

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [ ] I agree to contribute to the project under Apache 2 License.
- [ ] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [ ] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
2023-10-05 17:57:25 +03:00
Dmitry Kurtaev
c7ec0d599a
Merge pull request #23987 from dkurt:openvino_int8_backend
OpenVINO backend for INT8 models #23987

### Pull Request Readiness Checklist

TODO:
- [x] DetectionOutput layer (https://github.com/opencv/opencv/pull/24069)
- [x] Less FP32 fallbacks (i.e. Sigmoid, eltwise sum)
- [x] Accuracy, performance tests (https://github.com/opencv/opencv/pull/24039)
- [x] Single layer tests (convolution)
- [x] ~~Fixes for OpenVINO 2022.1 (https://pullrequest.opencv.org/buildbot/builders/precommit_custom_linux/builds/100334)~~


Performace results for object detection model `coco_efficientdet_lite0_v1_1.0_quant_2021_09_06.tflite`:
| backend | performance (median time) |
|---|---|
| OpenCV | 77.42ms |
| OpenVINO 2023.0 | 10.90ms |

CPU: `11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz`

Serialized model per-layer stats (note that Convolution should use `*_I8` primitives if they are quantized correctly): https://gist.github.com/dkurt/7772bbf1907035441bb5454f19f0feef

---

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
2023-09-28 16:24:43 +03:00
Zihao Mu
5025f29378
speed up vulkan dnn, and support ios and apple m1 chip. (#23349) 2023-05-18 20:02:27 +03:00
Zihao Mu
1e2ceca4df add enableWinograd API for Net. 2022-10-09 09:33:07 +08:00
wxsheng
4154bd0667
Add Loongson Advanced SIMD Extension support: -DCPU_BASELINE=LASX
* Add Loongson Advanced SIMD Extension support: -DCPU_BASELINE=LASX
* Add resize.lasx.cpp for Loongson SIMD acceleration
* Add imgwarp.lasx.cpp for Loongson SIMD acceleration
* Add LASX acceleration support for dnn/conv
* Add CV_PAUSE(v) for Loongarch
* Set LASX by default on Loongarch64
* LoongArch: tune test threshold for Core/HAL.mat_decomp/15

Co-authored-by: shengwenxue <shengwenxue@loongson.cn>
2022-09-10 09:39:43 +03:00
Zihao Mu
a80fcacd90
Merge pull request #21372 from zihaomu:dnn_quantize_per_tensor
Add per_tensor_quantize to int8 quantize

* add per_tensor_quantize to dnn int8 module.

* change api flag from perTensor to perChannel, and recognize quantize type and onnx importer.

* change the default to hpp
2022-07-05 19:14:42 +03:00
Zihao Mu
7b582b71ba
Merge pull request #21036 from fengyuentau:timvx_backend_support
dnn: TIM-VX NPU backend support

* Add TimVX NPU backend for DNN module.

* use official branch from tim-vx repo; fix detecting viv sdk

Co-authored-by: fytao <yuantao.feng@outlook.com>
2022-03-31 21:42:11 +00:00
SamFC10
87ebf2e50b fix illegal memory access in int8 convolution 2021-10-03 15:16:01 +05:30
SamFC10
fa90e14b06 int8 layers and 8-bit quantization support 2021-08-19 09:56:47 +05:30