Commit Graph

37 Commits

Author SHA1 Message Date
Dmitry Kurtaev
53f6198f27 Minor fixes in IE backend tests 2018-12-10 20:08:13 +03:00
Dmitry Kurtaev
b5c54e447c Extra hyperparameters for Intel's Inference Engine layers 2018-11-15 20:06:37 +03:00
Dmitry Kurtaev
e7015f6ae8 Fix ENet test 2018-10-19 17:43:26 +03:00
Dmitry Kurtaev
58ac3e09da Change default value of crop argument of blobFromImage from true to false 2018-09-12 19:02:58 +03:00
Vadim Pisarevsky
54279523a3 Merge pull request #12437 from vpisarev:avx2_fixes
* trying to fix the custom AVX2 builder test failures (false alarms)

* fixed compile error with CPU_BASELINE=AVX2 on x86; raised tolerance thresholds in a couple of tests

* fixed compile error with CPU_BASELINE=AVX2 on x86; raised tolerance thresholds in a couple of tests

* fixed compile error with CPU_BASELINE=AVX2 on x86; raised tolerance thresholds in a couple of tests

* seemingly disabled false alarm warning in surf.cpp; increased tolerance thresholds in the tests for SolvePnP and in DNN/ENet
2018-09-06 18:56:55 +03:00
Dmitry Kurtaev
d486204a0d Merge pull request #12264 from dkurt:dnn_remove_forward_method
* Remove a forward method in dnn::Layer

* Add a test

* Fix tests

* Mark multiple dnn::Layer::finalize methods as deprecated

* Replace back dnn's inputBlobs to vector of pointers

* Remove Layer::forward_fallback from CV_OCL_RUN scopes
2018-09-06 13:26:47 +03:00
Dmitry Kurtaev
6ec230480d Enable Myriad tests with batch size > 1 2018-09-05 10:45:09 +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
Dmitry Kurtaev
3e027df583 Enable more deep learning tests using Intel's Inference Engine backend 2018-08-27 18:37:35 +03:00
Dmitry Kurtaev
faa6c4e1e1 Faster-RCNN anf RFCN models on CPU using Intel's Inference Engine backend.
Enable Torch layers tests with Intel's Inference Engine backend.
2018-07-25 19:04:55 +03:00
Alexander Alekhin
452fa3011c dnn(test): drop CV_ENUM for DNNBackend / DNNTarget 2018-07-10 15:12:01 +03:00
Dmitry Kurtaev
019c2f2115 Enable more deep learning tests 2018-07-05 14:23:15 +03:00
Dmitry Kurtaev
40b85c1cd9 Remove undocumented feature to retreive layers outputs by indices 2018-06-20 14:44:21 +03:00
Dmitry Kurtaev
2c291bc2fb Enable FastNeuralStyle and OpenFace networks with IE backend 2018-06-09 15:57:12 +03:00
Vadim Pisarevsky
3cbd2e2764 Merge pull request #11650 from dkurt:dnn_default_backend 2018-06-06 09:30:39 +00:00
Dmitry Kurtaev
b781ac7346 Make Intel's Inference Engine backend is default if no preferable backend is specified. 2018-06-04 18:31:46 +03:00
Kuang Fangjun
9ae28415ec fix doc. 2018-06-03 17:44:24 +08:00
Dmitry Kurtaev
4ec456f0a0 Custom layers for deep learning networks (#11129)
* Custom deep learning layers support

* Stack custom deep learning layers
2018-04-24 14:59:59 +03:00
Alexander Alekhin
f95e91e2bc Merge pull request #11199 from dkurt:update_torch_testdata 2018-04-03 18:02:58 +00:00
Dmitry Kurtaev
818a91f4f7 Update Torch testdata 2018-03-31 12:04:44 +03:00
Dmitry Kurtaev
598039c0ed Fix embedded Torch's nn.ConcatTable 2018-03-31 11:11:10 +03:00
Dmitry Kurtaev
0a61ebdd66 Replace DNNTarget and DNNBackend in tests 2018-03-07 12:59:38 +03:00
Dmitry Kurtaev
e1c3237532 Parametric OpenCL deep learning tests 2018-03-05 20:53:18 +03:00
Alexander Alekhin
4a297a2443 ts: refactor OpenCV tests
- removed tr1 usage (dropped in C++17)
- moved includes of vector/map/iostream/limits into ts.hpp
- require opencv_test + anonymous namespace (added compile check)
- fixed norm() usage (must be from cvtest::norm for checks) and other conflict functions
- added missing license headers
2018-02-03 19:39:47 +00:00
Li Peng
2124361ff7 ocl support for Deconvolution layer
Signed-off-by: Li Peng <peng.li@intel.com>
2018-01-18 23:40:22 +08:00
Li Peng
e3b42bf93b batch_norm and blank layer ocl implementation
Signed-off-by: Li Peng <peng.li@intel.com>
2018-01-09 21:58:46 +08:00
Li Peng
67f9406cbe add normalize_bbox layer ocl implementation
Signed-off-by: Li Peng <peng.li@intel.com>
2018-01-05 19:38:36 +08:00
Dmitry Kurtaev
6aabd6cc7a Remove cv::dnn::Importer 2017-12-18 18:08:28 +03:00
Dmitry Kurtaev
bbbec300a6 nn.BatchNormalization and nn.Dropout layers from Torch 2017-12-04 12:57:21 +03:00
Li Peng
a47fbd2610 Add ocl accuracy test for a few dnn nets
They are alexnet, mobilenet-ssd, resnet50, squeezeNet_v1_1,
yolo and fast_neural_style.

Signed-off-by: Li Peng <peng.li@intel.com>
2017-11-27 23:33:21 +08:00
Dmitry Kurtaev
4b52b8df34 Layers for fast-neural-style models: https://github.com/jcjohnson/fast-neural-style 2017-10-27 14:26:45 +03:00
Dmitry Kurtaev
410d44d67d Binary data for batch normalization test from Torch 2017-10-20 12:01:42 +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
222149b9c6 Refactored Padding layer 2017-09-22 12:39:00 +03:00
Dmitry Kurtaev
bd8e6b7e14 Make external cv::dnn::Importer usage is deprecated 2017-09-18 08:52:36 +03:00
Dmitry Kurtaev
7dc6b1d7d4 Layers for OpenFace face recognition network 2017-09-14 09:11:31 +03:00
Alexander Alekhin
93729784bb dnn: move module from opencv_contrib
e6f63c7a38/modules/dnn
2017-06-26 13:41:51 +03:00