Commit Graph

87 Commits

Author SHA1 Message Date
Alexander Alekhin
fcb07c64f3 cmake: fix build of dnn tests with shared common code
- don't share .cpp files (PCH support is broken)
2019-03-31 08:52:25 +00:00
Sayed Adel
de22442046 dnn:perf add missing definition __OPENCV_TEST to fix pch 2019-03-31 03:28:33 +02:00
Lubov Batanina
7d3d6bc4e2 Merge pull request #13932 from l-bat:MyriadX_master_dldt
* Fix precision in tests for MyriadX

* Fix ONNX tests

* Add output range in ONNX tests

* Skip tests on Myriad OpenVINO 2018R5

* Add detect MyriadX

* Add detect MyriadX on OpenVINO R5

* Skip tests on Myriad next version of OpenVINO

* dnn(ie): VPU type from environment variable

* dnn(test): validate VPU type

* dnn(test): update DLIE test skip conditions
2019-03-29 16:42:58 +03:00
Alexander Alekhin
96c71dd3d2 dnn: reduce set of ignored warnings 2018-11-15 13:15:59 +03:00
Dmitry Kurtaev
c8f3579f93 Fix #12542 (#12603)
* Fix #12542

* Remove ignore of non-virtual-dtor error
2018-09-26 16:08:51 +03:00
Alexander Alekhin
29bee6f07e cmake: move Matlab scripts to opencv_contrib (#12541)
* matlab: move to opencv_contrib

* cmake: preserve variables scope for processing modules

- use macro instead of function to avoid scope resets
2018-09-17 14:55:42 +03:00
Lubov Batanina
0c8590027f Merge pull request #12071 from l-bat/l-bat:onnx_parser
* Add Squeezenet support in ONNX

* Add AlexNet support in ONNX

* Add Googlenet support in ONNX

* Add CaffeNet and RCNN support in ONNX

* Add VGG16 and VGG16 with batch normalization support in ONNX

* Add RCNN, ZFNet, ResNet18v1 and ResNet50v1 support in ONNX

* Add ResNet101_DUC_HDC

* Add Tiny Yolov2

* Add CNN_MNIST, MobileNetv2 and LResNet100 support in ONNX

* Add ONNX models for emotion recognition

* Add DenseNet121 support in ONNX

* Add Inception v1 support in ONNX

* Refactoring

* Fix tests

* Fix tests

* Skip unstable test

* Modify Reshape operation
2018-09-10 21:07:51 +03:00
Dmitry Kurtaev
50bceea038 Include preprocessing nodes to object detection TensorFlow networks (#12211)
* Include preprocessing nodes to object detection TensorFlow networks

* Enable more fusion

* faster_rcnn_resnet50_coco_2018_01_28 test
2018-08-31 15:41:56 +03:00
Maksim Shabunin
7cf52de47e dnn: modified IE search, R2 compatibility fixed 2018-07-31 14:48:06 +03:00
Dmitry Kurtaev
28e08ae0bd Add a sample which tests OpenVINO models 2018-07-23 19:08:51 +03:00
Alexander Alekhin
e2b5d11290 dnn: allow to use external protobuf
"custom layers" feature will not work properly in these builds.
2018-07-09 17:28:45 +03:00
Vadim Pisarevsky
dc27d52221
temporarily disabled OpenCL use in DNN module on Mac (#11828)
* temporarily disabled OpenCL use in DNN module on Mac, since some of the tests fail

* disable OpenCL in DNN on Mac at CMake level, not source level (thanks to alalek for the advice)
2018-06-26 09:35:18 +03:00
Maksim Shabunin
020ad1ac76 dnn: allow setting IE paths via command line 2018-05-22 14:40:03 +03:00
Alexander Alekhin
6c8014e7d1 cmake: disable checks for protobuf generated files 2018-03-28 18:43:28 +03:00
Dmitry Kurtaev
2f3a9ba1d4 Update OpenCVDetectInferenceEngine.cmake 2018-03-28 16:34:37 +03:00
Alexander Alekhin
1b83bc48a1 dnn: make OpenCL DNN code optional 2018-03-01 12:12:40 +03:00
luz.paz
5718d09e39 Misc. modules/ typos
Found via `codespell`
2018-02-12 07:09:43 -05:00
Alexander Alekhin
5a791e6e06 cmake: update reporting of excluded dispatching files (#10711)
* cmake: add ocv_get_smart_file_name() macro

* cmake: avoid adding files for unavailable dispatch modes
2018-02-12 14:48:20 +03:00
Dmitry Kurtaev
10e1de74d2 Intel Inference Engine deep learning backend (#10608)
* Intel Inference Engine deep learning backend.

* OpenFace network using Inference Engine backend
2018-02-06 11:57:35 +03:00
Alexander Alekhin
3d6659112f cmake: fix includes processing 2018-02-02 21:52:54 +03:00
Maksim Shabunin
e56d6054aa Do not build protobuf without dnn (#10689)
* Do not build protobuf if dnn is disabled

* Added BUILD_LIST cmake option to the cache

* Moved protobuf to the top level

* Fixed static build

* Fixed world build

* fixup! Fixed world build
2018-02-01 16:30:23 +03:00
Alexander Alekhin
4d84999452 dnn: protobuf build warnings 2018-01-15 21:15:23 +00:00
Alexander Alekhin
6674a024fc dnn: add OPENCV_DNN_DISABLE_MEMORY_OPTIMIZATIONS runtime option
replaces REUSE_DNN_MEMORY compile-time option
2018-01-07 18:38:14 +00:00
Alexander Alekhin
7d67d60fb1 cmake(opt): AVX512_SKX 2017-12-29 07:18:11 +00:00
Alexander Alekhin
8e7af7f089 Merge pull request #10456 from dkurt:dnn_allocate_mem_for_optimized_concat 2017-12-28 16:04:51 +00:00
Alexander Alekhin
898ca38257 cmake: AVX512 -> AVX_512F 2017-12-28 15:20:27 +00:00
Dmitry Kurtaev
a9807d8f54 Allocate new memory for optimized concat to prevent collisions.
Add a flag to disable memory reusing in dnn module.
2017-12-28 16:45:53 +03:00
Arjan van de Ven
2938860b3f Provide a few AVX512 optimized functions for the DNN module
This patch adds AVX512 optimized fastConv as well as the hookups
needed to get these called in the convolution_layer.

AVX512 fastConv is code-identical on a C level to the AVX2 one,
but is measurably faster due to AVX512 having more registers available
to cache results in.

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
2017-12-26 16:00:17 +00:00
Dmitry Kurtaev
6aabd6cc7a Remove cv::dnn::Importer 2017-12-18 18:08:28 +03:00
Dmitry Kurtaev
f503515082 JavaScript bindings for dnn module 2017-12-08 18:33:48 +03:00
Alexander Alekhin
f6d927ef3b dnn: avoid conflicts with original caffe.proto
rename caffe.proto => opencv-caffe.proto
2017-11-20 19:04:00 +03:00
pengli
e340ff9c3a Merge pull request #9114 from pengli:dnn_rebase
add libdnn acceleration to dnn module  (#9114)

* import libdnn code

Signed-off-by: Li Peng <peng.li@intel.com>

* add convolution layer ocl acceleration

Signed-off-by: Li Peng <peng.li@intel.com>

* add pooling layer ocl acceleration

Signed-off-by: Li Peng <peng.li@intel.com>

* add softmax layer ocl acceleration

Signed-off-by: Li Peng <peng.li@intel.com>

* add lrn layer ocl acceleration

Signed-off-by: Li Peng <peng.li@intel.com>

* add innerproduct layer ocl acceleration

Signed-off-by: Li Peng <peng.li@intel.com>

* add HAVE_OPENCL macro

Signed-off-by: Li Peng <peng.li@intel.com>

* fix for convolution ocl

Signed-off-by: Li Peng <peng.li@intel.com>

* enable getUMat() for multi-dimension Mat

Signed-off-by: Li Peng <peng.li@intel.com>

* use getUMat for ocl acceleration

Signed-off-by: Li Peng <peng.li@intel.com>

* use CV_OCL_RUN macro

Signed-off-by: Li Peng <peng.li@intel.com>

* set OPENCL target when it is available

and disable fuseLayer for OCL target for the time being

Signed-off-by: Li Peng <peng.li@intel.com>

* fix innerproduct accuracy test

Signed-off-by: Li Peng <peng.li@intel.com>

* remove trailing space

Signed-off-by: Li Peng <peng.li@intel.com>

* Fixed tensorflow demo bug.

Root cause is that tensorflow has different algorithm with libdnn
to calculate convolution output dimension.

libdnn don't calculate output dimension anymore and just use one
passed in by config.

* split gemm ocl file

split it into gemm_buffer.cl and gemm_image.cl

Signed-off-by: Li Peng <peng.li@intel.com>

* Fix compile failure

Signed-off-by: Li Peng <peng.li@intel.com>

* check env flag for auto tuning

Signed-off-by: Li Peng <peng.li@intel.com>

* switch to new ocl kernels for softmax layer

Signed-off-by: Li Peng <peng.li@intel.com>

* update softmax layer

on some platform subgroup extension may not work well,
fallback to non subgroup ocl acceleration.

Signed-off-by: Li Peng <peng.li@intel.com>

* fallback to cpu path for fc layer with multi output

Signed-off-by: Li Peng <peng.li@intel.com>

* update output message

Signed-off-by: Li Peng <peng.li@intel.com>

* update fully connected layer

fallback to gemm API if libdnn return false

Signed-off-by: Li Peng <peng.li@intel.com>

* Add ReLU OCL implementation

* disable layer fusion for now

Signed-off-by: Li Peng <peng.li@intel.com>

* Add OCL implementation for concat layer

Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com>

* libdnn: update license and copyrights

Also refine libdnn coding style

Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com>
Signed-off-by: Li Peng <peng.li@intel.com>

* DNN: Don't link OpenCL library explicitly

* DNN: Make default preferableTarget to DNN_TARGET_CPU

User should set it to DNN_TARGET_OPENCL explicitly if want to
use OpenCL acceleration.

Also don't fusion when using DNN_TARGET_OPENCL

* DNN: refine coding style

* Add getOpenCLErrorString

* DNN: Use int32_t/uint32_t instread of alias

* Use namespace ocl4dnn to include libdnn things

* remove extra copyTo in softmax ocl path

Signed-off-by: Li Peng <peng.li@intel.com>

* update ReLU layer ocl path

Signed-off-by: Li Peng <peng.li@intel.com>

* Add prefer target property for layer class

It is used to indicate the target for layer forwarding,
either the default CPU target or OCL target.

Signed-off-by: Li Peng <peng.li@intel.com>

* Add cl_event based timer for cv::ocl

* Rename libdnn to ocl4dnn

Signed-off-by: Li Peng <peng.li@intel.com>
Signed-off-by: wzw <zhiwen.wu@intel.com>

* use UMat for ocl4dnn internal buffer

Remove allocateMemory which use clCreateBuffer directly

Signed-off-by: Li Peng <peng.li@intel.com>
Signed-off-by: wzw <zhiwen.wu@intel.com>

* enable buffer gemm in ocl4dnn innerproduct

Signed-off-by: Li Peng <peng.li@intel.com>

* replace int_tp globally for ocl4dnn kernels.

Signed-off-by: wzw <zhiwen.wu@intel.com>
Signed-off-by: Li Peng <peng.li@intel.com>

* create UMat for layer params

Signed-off-by: Li Peng <peng.li@intel.com>

* update sign ocl kernel

Signed-off-by: Li Peng <peng.li@intel.com>

* update image based gemm of inner product layer

Signed-off-by: Li Peng <peng.li@intel.com>

* remove buffer gemm of inner product layer

call cv::gemm API instead

Signed-off-by: Li Peng <peng.li@intel.com>

* change ocl4dnn forward parameter to UMat

Signed-off-by: Li Peng <peng.li@intel.com>

* Refine auto-tuning mechanism.

- Use OPENCV_OCL4DNN_KERNEL_CONFIG_PATH to set cache directory
  for fine-tuned kernel configuration.
  e.g. export OPENCV_OCL4DNN_KERNEL_CONFIG_PATH=/home/tmp,
  the cache directory will be /home/tmp/spatialkernels/ on Linux.

- Define environment OPENCV_OCL4DNN_ENABLE_AUTO_TUNING to enable
  auto-tuning.

- OPENCV_OPENCL_ENABLE_PROFILING is only used to enable profiling
  for OpenCL command queue. This fix basic kernel get wrong running
  time, i.e. 0ms.

- If creating cache directory failed, disable auto-tuning.

* Detect and create cache dir on windows

Signed-off-by: Li Peng <peng.li@intel.com>

* Refine gemm like convolution kernel.

Signed-off-by: Li Peng <peng.li@intel.com>

* Fix redundant swizzleWeights calling when use cached kernel config.

* Fix "out of resource" bug when auto-tuning too many kernels.

* replace cl_mem with UMat in ocl4dnnConvSpatial class

* OCL4DNN: reduce the tuning kernel candidate.

This patch could reduce 75% of the tuning candidates with less
than 2% performance impact for the final result.

Signed-off-by: Zhigang Gong <zhigang.gong@intel.com>

* replace cl_mem with umat in ocl4dnn convolution

Signed-off-by: Li Peng <peng.li@intel.com>

* remove weight_image_ of ocl4dnn inner product

Actually it is unused in the computation

Signed-off-by: Li Peng <peng.li@intel.com>

* Various fixes for ocl4dnn

1. OCL_PERFORMANCE_CHECK(ocl::Device::getDefault().isIntel())
2. Ptr<OCL4DNNInnerProduct<float> > innerProductOp
3. Code comments cleanup
4. ignore check on OCL cpu device

Signed-off-by: Li Peng <peng.li@intel.com>

* add build option for log softmax

Signed-off-by: Li Peng <peng.li@intel.com>

* remove unused ocl kernels in ocl4dnn

Signed-off-by: Li Peng <peng.li@intel.com>

* replace ocl4dnnSet with opencv setTo

Signed-off-by: Li Peng <peng.li@intel.com>

* replace ALIGN with cv::alignSize

Signed-off-by: Li Peng <peng.li@intel.com>

* check kernel build options

Signed-off-by: Li Peng <peng.li@intel.com>

* Handle program compilation fail properly.

* Use std::numeric_limits<float>::infinity() for large float number

* check ocl4dnn kernel compilation result

Signed-off-by: Li Peng <peng.li@intel.com>

* remove unused ctx_id

Signed-off-by: Li Peng <peng.li@intel.com>

* change clEnqueueNDRangeKernel to kernel.run()

Signed-off-by: Li Peng <peng.li@intel.com>

* change cl_mem to UMat in image based gemm

Signed-off-by: Li Peng <peng.li@intel.com>

* check intel subgroup support for lrn and pooling layer

Signed-off-by: Li Peng <peng.li@intel.com>

* Fix convolution bug if group is greater than 1

Signed-off-by: Li Peng <peng.li@intel.com>

* Set default layer preferableTarget to be DNN_TARGET_CPU

Signed-off-by: Li Peng <peng.li@intel.com>

* Add ocl perf test for convolution

Signed-off-by: Li Peng <peng.li@intel.com>

* Add more ocl accuracy test

Signed-off-by: Li Peng <peng.li@intel.com>

* replace cl_image with ocl::Image2D

Signed-off-by: Li Peng <peng.li@intel.com>

* Fix build failure in elementwise layer

Signed-off-by: Li Peng <peng.li@intel.com>

* use getUMat() to get blob data

Signed-off-by: Li Peng <peng.li@intel.com>

* replace cl_mem handle with ocl::KernelArg

Signed-off-by: Li Peng <peng.li@intel.com>

* dnn(build): don't use C++11, OPENCL_LIBRARIES fix

* dnn(ocl4dnn): remove unused OpenCL kernels

* dnn(ocl4dnn): extract OpenCL code into .cl files

* dnn(ocl4dnn): refine auto-tuning

Defaultly disable auto-tuning, set OPENCV_OCL4DNN_ENABLE_AUTO_TUNING
environment variable to enable it.

Use a set of pre-tuned configs as default config if auto-tuning is disabled.
These configs are tuned for Intel GPU with 48/72 EUs, and for googlenet,
AlexNet, ResNet-50

If default config is not suitable, use the first available kernel config
from the candidates. Candidate priority from high to low is gemm like kernel,
IDLF kernel, basick kernel.

* dnn(ocl4dnn): pooling doesn't use OpenCL subgroups

* dnn(ocl4dnn): fix perf test

OpenCV has default 3sec time limit for each performance test.
Warmup OpenCL backend outside of perf measurement loop.

* use ocl::KernelArg as much as possible

Signed-off-by: Li Peng <peng.li@intel.com>

* dnn(ocl4dnn): fix bias bug for gemm like kernel

* dnn(ocl4dnn): wrap cl_mem into UMat

Signed-off-by: Li Peng <peng.li@intel.com>

* dnn(ocl4dnn): Refine signature of kernel config

- Use more readable string as signture of kernel config
- Don't count device name and vendor in signature string
- Default kernel configurations are tuned for Intel GPU with
  24/48/72 EUs, and for googlenet, AlexNet, ResNet-50 net model.

* dnn(ocl4dnn): swap width/height in configuration

* dnn(ocl4dnn): enable configs for Intel OpenCL runtime only

* core: make configuration helper functions accessible from non-core modules

* dnn(ocl4dnn): update kernel auto-tuning behavior

Avoid unwanted creation of directories

* dnn(ocl4dnn): simplify kernel to workaround OpenCL compiler crash

* dnn(ocl4dnn): remove redundant code

* dnn(ocl4dnn): Add more clear message for simd size dismatch.

* dnn(ocl4dnn): add const to const argument

Signed-off-by: Li Peng <peng.li@intel.com>

* dnn(ocl4dnn): force compiler use a specific SIMD size for IDLF kernel

* dnn(ocl4dnn): drop unused tuneLocalSize()

* dnn(ocl4dnn): specify OpenCL queue for Timer and convolve() method

* dnn(ocl4dnn): sanitize file names used for cache

* dnn(perf): enable Network tests with OpenCL

* dnn(ocl4dnn/conv): drop computeGlobalSize()

* dnn(ocl4dnn/conv): drop unused fields

* dnn(ocl4dnn/conv): simplify ctor

* dnn(ocl4dnn/conv): refactor kernelConfig localSize=NULL

* dnn(ocl4dnn/conv): drop unsupported double / untested half types

* dnn(ocl4dnn/conv): drop unused variable

* dnn(ocl4dnn/conv): alignSize/divUp

* dnn(ocl4dnn/conv): use enum values

* dnn(ocl4dnn): drop unused innerproduct variable

Signed-off-by: Li Peng <peng.li@intel.com>

* dnn(ocl4dnn): add an generic function to check cl option support

* dnn(ocl4dnn): run softmax subgroup version kernel first

Signed-off-by: Li Peng <peng.li@intel.com>
2017-10-02 15:38:00 +03:00
Dmitry Kurtaev
5c43a394c5 Added performance test for Caffe framework 2017-08-27 19:40:58 +03:00
Alexander Alekhin
cbced23de4 cmake: don't include protobuf on disabled DNN module 2017-07-31 14:18:59 +03:00
Alexander Alekhin
4784c7be5f dnn: cleanup dispatched code, fix SIMD128 types 2017-07-13 19:00:34 +03:00
abratchik
8f7181429f add java wrappers to dnn module 2017-07-02 11:46:20 +04:00
Alexander Alekhin
93729784bb dnn: move module from opencv_contrib
e6f63c7a38/modules/dnn
2017-06-26 13:41:51 +03:00