Commit Graph

115 Commits

Author SHA1 Message Date
Dmitry Kurtaev
0d117312c9 DNN_TARGET_FPGA using Intel's Inference Engine 2018-11-19 11:41:43 +03:00
Alexander Alekhin
f2bec05e6d Merge pull request #12913 from dkurt:dnn_fix_ie_hyperparams 2018-11-16 18:36:12 +00:00
Dmitry Kurtaev
b5c54e447c Extra hyperparameters for Intel's Inference Engine layers 2018-11-15 20:06:37 +03:00
Alexander Alekhin
96c71dd3d2 dnn: reduce set of ignored warnings 2018-11-15 13:15:59 +03:00
Dmitry Kurtaev
09fa758725 Replace Darknet's Reorg to permute layer 2018-09-12 18:13:39 +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
3e027df583 Enable more deep learning tests using Intel's Inference Engine backend 2018-08-27 18:37:35 +03:00
Alexander Alekhin
d2e08a524e core: repair CV_Assert() messages
Multi-argument CV_Assert() is accessible via CV_Assert_N() (with malformed messages).
2018-08-15 17:43:10 +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
Dmitry Kurtaev
070393dfda uint8 inputs for deep learning networks 2018-07-19 14:37:33 +03:00
Dmitry Kurtaev
dcc1beb1f8 Clip kernel for OpenCL PriorBox layer 2018-07-13 14:49:13 +03:00
Alexander Alekhin
529d38613b Merge pull request #11923 from alalek:dnn_external_protobuf 2018-07-09 16:07:42 +00:00
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
Alexander Alekhin
52b151dceb dnn(test): use checkMyriadTarget() in Test_Caffe_layers.Conv_Elu test 2018-07-09 16:20:46 +03:00
Vadim Pisarevsky
523b6f32ba Merge pull request #11867 from dkurt:dnn_ie_layers 2018-07-06 13:13:20 +00:00
Dmitry Kurtaev
019c2f2115 Enable more deep learning tests 2018-07-05 14:23:15 +03:00
Dmitry Kurtaev
f25a01bb5a Disable fusion to output layers 2018-07-04 15:53:47 +03:00
Dmitry Kurtaev
7ed5d85f25 Add Reshape layer tests 2018-07-03 08:26:43 +03:00
Dmitry Kurtaev
346871e27f Set output layers names and types for models in DLDT's intermediate representation 2018-06-28 10:21:45 +03:00
Dmitry Kurtaev
b11e22c25b Update Inference Engine tests 2018-06-26 15:38:08 +03:00
Dmitry Kurtaev
e8e9d1d021 Implement Interp layer using Resize layer 2018-06-22 19:26:47 +03:00
Dmitry Kurtaev
4626246087 Add ShuffleChannel layer 2018-06-21 19:10:42 +03:00
Dmitry Kurtaev
40b85c1cd9 Remove undocumented feature to retreive layers outputs by indices 2018-06-20 14:44:21 +03:00
Dmitry Kurtaev
40765c5f8d Enable SSD models from TensorFlow with OpenCL plugin of Intel's Inference Engine 2018-06-08 16:55:21 +03:00
rockzhan
1187a7fa34 Merge pull request #11649 from rockzhan:dnn_dw_prelu
dnn: Fix output mismatch when forward dnn model contain [depthwise conv(group=1) + bn + prelu]  (#11649)

* this can make sure [depthwise conv(group=1) + bn + prelu] output not shift

* add TEST to show the output mismatch in [DWconv+Prelu]

* fix typo

* change loading image to init cvMat directly

* build runtime model, without loading external model

* remove whitespace

* change way to create a cvmat

* add bias_term, add target output

* fix [dwconv + prelu] value mismatch when no optimizations

* fix Test error when change output channels

* add parametric test

* change num_output to group value

* change conv code and change test back
2018-06-07 13:45:54 +00:00
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
Dmitry Kurtaev
ab389142af Fix multiple networks with Intel's Inference Engine backend 2018-06-01 14:10:32 +03:00
Dmitry Kurtaev
32bab45f81 Fix Inference Engine graphs with fused output layers 2018-05-31 16:21:08 +03:00
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
Dmitry Kurtaev
4ef6c91583 Fix multiple inputs for models from Intel's Model Optimizer 2018-04-11 13:28:07 +03:00
Dmitry Kurtaev
ef1aaf12c9 Fix Proposal deep learning layer 2018-04-04 14:48:29 +03:00
Alexander Alekhin
e8a67de0d2 Merge pull request #11182 from dkurt:fix_11102_part_2 2018-03-30 13:11:01 +00:00
Dmitry Kurtaev
e039fc3a63 Replace protobuf's ReleaseLast to RemoveLast to deallocate memory.
Change an order of PriorBox layer operations.
2018-03-28 17:27:36 +03:00
Dmitry Kurtaev
7972f47ed4 Load networks from intermediate representation of Intel's Deep learning deployment toolkit. 2018-03-26 07:24:21 +03:00
Dmitry Kurtaev
e8fe6ee4e3 Fix prior box generation in case of squared proposals.
Fix batch norm in training phase.
2018-03-23 09:44:59 +03:00
Dmitry Kurtaev
f8d0d6365e Add a flag to manage average pooling with padding 2018-02-14 16:56:31 +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
7a4c5e9421 slice layer ocl support
Signed-off-by: Li Peng <peng.li@intel.com>
2018-01-29 22:34:32 +08:00
Alexander Alekhin
c3569211d5 Merge pull request #10591 from drkoller:master 2018-01-19 09:44:21 +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
David Koller
d1a3b530be Make DNN Crop layer match Caffe default offset behavior
and add parametric unit test for crop layer.
2018-01-17 10:52:36 -05:00
Li Peng
e77af4ae33 MVN layer ocl implementation
Signed-off-by: Li Peng <peng.li@intel.com>
2018-01-17 17:11:32 +08:00
Li Peng
7bc017601f Power, Tanh and Channels ReLU layer ocl support
Signed-off-by: Li Peng <peng.li@intel.com>
2018-01-17 17:11:27 +08:00
Dmitry Kurtaev
1f4fdfd599 Untrainable version of Scale layer from Caffe 2018-01-13 10:35:29 +03:00
Li Peng
f99a135eda add eltwise layer ocl implementation
Signed-off-by: Li Peng <peng.li@intel.com>
2018-01-05 19:38:30 +08:00
Alexander Alekhin
2b3c140f04
Merge pull request #10436 from alalek:test_threads 2017-12-28 18:29:30 +03:00
Li Peng
00f03c5739 Add ocl version FasterRCNN accuracy test
Signed-off-by: Li Peng <peng.li@intel.com>
2017-12-28 19:15:15 +08:00
Alexander Alekhin
9b131b5f7e dnn(test): avoid calling of cv::setNumThreads() in tests directly
It is not necessary by default.
Also it breaks test system command-line parameters: --perf_threads / --test_threads
2017-12-27 15:16:41 +00:00
Dmitry Kurtaev
70c605a03d Limit Concat layer optimization 2017-12-26 16:49:33 +03:00
Dmitry Kurtaev
08112f3821 Faster-RCNN models support 2017-12-15 12:16:21 +03:00
Dmitry Kurtaev
17dcf0e82d ROIPooling layer 2017-12-07 19:04:38 +03:00
Dmitry Kurtaev
20a2dc6ac5 Fix multiple inputs models from Caffe.
Fixed Concat optimization.
2017-11-02 18:55:08 +03:00
Dmitry Kurtaev
a36ebaecdc PReLU layer for multidimensional input 2017-10-23 16:13:03 +03:00
Vadim Pisarevsky
b7ff9ddcdd Merge pull request #9705 from AlexeyAB:dnn_darknet_yolo_v2 2017-10-10 12:02:03 +00:00
AlexeyAB
ecc34dc521 Added DNN Darknet Yolo v2 for object detection 2017-10-09 21:08:44 +03:00
Dmitry Kurtaev
eabf728682 PReLU layer from Caffe 2017-10-09 20:30:37 +03:00
Dmitry Kurtaev
ad8bbaf008 Multidimensional eltwise layer.
Fixed fully-connected layer axis.
2017-10-04 14:01:44 +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
84cec17913 LSTM layer for TensorFlow importer 2017-09-26 12:59:36 +03:00
Dmitry Kurtaev
17a85b16fc Remove reorder_dims attribute of Reshape layer 2017-09-21 16:42:03 +03:00
Dmitry Kurtaev
bd8e6b7e14 Make external cv::dnn::Importer usage is deprecated 2017-09-18 08:52:36 +03:00
Aleksandr Rybnikov
8d6b8b45b6 Added ELU and test for it 2017-08-02 11:13:59 +03:00
Alexander Alekhin
93729784bb dnn: move module from opencv_contrib
e6f63c7a38/modules/dnn
2017-06-26 13:41:51 +03:00