mirror/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2024-12-16 02:19:12 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity
33,330 Commits 6 Branches 127 Tags 3 GiB
62c0556c58
Commit Graph

1718 Commits

Author SHA1 Message Date
Alexander Alekhin
596a0125ed Merge pull request #12336 from dkurt:dnn_ie_fix_net_lifetime 2018-08-30 11:09:18 +00:00
Wu Zhiwen
ca51bbb7ff dnn: fix variance setting bug for PriorBoxLayer 
- The size of second channel should be size[2] of output tensor,
- The Scalar should be {variance[0], variance[0], variance[0], variance[0]}
  for _variance.size() == 1 case.

Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com>
 2018-08-30 11:05:38 +08:00
Dmitry Kurtaev
4062ef5fcb Fix lifetime of networks which are loaded from Model Optimizer IRs 2018-08-29 13:34:26 +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
7f73b105ca core: std::string more changes 2018-08-27 15:41:01 +03:00
Dmitry Kurtaev
472b71ecef Merge pull request #12243 from dkurt:dnn_tf_mask_rcnn 
* Support Mask-RCNN from TensorFlow

* Fix a sample
 2018-08-24 14:47:32 +03:00
Alexander Alekhin
096366738b dnn(build): fix CV_Assert() usage 2018-08-22 16:04:40 +03:00
Alexander Alekhin
c9faa09d55 Merge pull request #12266 from mshabunin:fix-windows-ie-build 2018-08-21 13:07:44 +00:00
Maksim Shabunin
808c89adc1 Fixed windows build with InferenceEngine 2018-08-21 14:59:13 +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
Alexander Alekhin
b9b66ca437 Merge pull request #12205 from dkurt:dnn_update_tf_face_detection 2018-08-14 10:53:12 +00:00
Dmitry Kurtaev
f056c0f137 UINT8 face detection network using Intel's Inference Engine backend 2018-08-13 18:38:47 +03:00
Alexander Alekhin
615883977f Merge pull request #12128 from dkurt:dnn_fix_12066 2018-08-10 14:14:16 +00:00
Vadim Pisarevsky
7c8ab271fc Merge pull request #12125 from dkurt:dnn_mobilenet_ppn 2018-08-06 14:40:50 +00:00
Vadim Pisarevsky
70b893333d Merge pull request #12130 from dkurt:dnn_ie_mvn 2018-08-06 14:37:46 +00:00
Dmitry Kurtaev
449696f1e5 Enable reshape-as-shape layer from TensorFlow 2018-08-06 17:35:06 +03:00
Vadim Pisarevsky
e0c93bcf6c Merge pull request #12082 from dkurt:dnn_ie_faster_rcnn 2018-08-06 14:28:58 +00:00
Alexander Alekhin
ac4a6aad15 Merge pull request #12050 from alalek:dnn_ocl_avoid_memory_access_violation 2018-08-05 14:47:01 +00:00
Dmitry Kurtaev
be08730cd6 MVN layer using Intel's Inference Engine backend 2018-08-02 17:49:03 +03:00
Dmitry Kurtaev
4fb086d6c3 MobileNet-SSD v1 from TensorFlow with shared convolution weights 2018-08-01 16:16:48 +03:00
Dmitry Kurtaev
8e034053af Faster-RCNN from TensorFlow on CPU with Intel's Inference Engine backend 2018-08-01 11:29:58 +03:00
Alexander Alekhin
814ebe39ae Merge pull request #12113 from dkurt:dnn_fix_ssd_on_myriad 2018-07-31 14:55:18 +00:00
Maksim Shabunin
7cf52de47e dnn: modified IE search, R2 compatibility fixed 2018-07-31 14:48:06 +03:00
Dmitry Kurtaev
ed0e79cb61 Add missing parameter to DetectionOutput layer from Intel's Inference Engine 2018-07-31 11:37:45 +03:00
Maksim Shabunin
fb1f12021b Fixed build with latest IE version 2018-07-27 19:56:35 +03:00
Alexander Alekhin
b597c87bed dnn(ocl): avoid memory access violation 2018-07-27 15:35:11 +03:00
Alexander Alekhin
9137e2d635 Merge pull request #12060 from alalek:dnn_debug_layers 2018-07-26 15:14:32 +00:00
Alexander Alekhin
c37d1a53b5 Merge pull request #12025 from Triplesalt:tfimport-relu 2018-07-26 15:08:05 +00:00
Triplesalt
9eb79926df Allow a different input order for Mul+Maximum. 
Squashed : ReLU operand order tests.
 2018-07-26 14:19:11 +02:00
Vadim Pisarevsky
fa466b022d Merge pull request #12052 from dkurt:dnn_ie_torch_tests 2018-07-26 09:09:35 +00:00
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
45b5b3c13a dnn: check layer output for NaN/Inf 2018-07-25 16:25:18 +03:00
Maksim Shabunin
cbb1e867e5 More issues found by static analysis 2018-07-24 16:04:42 +03:00
Alexander Alekhin
8de08e0463 Merge pull request #12021 from dkurt:dnn_ie_tf_ssd 2018-07-24 13:03:41 +00:00
Alexander Alekhin
236f383969 Merge pull request #12037 from dkurt:test_openvino_models 2018-07-24 12:34:04 +00:00
Dmitry Kurtaev
28e08ae0bd Add a sample which tests OpenVINO models 2018-07-23 19:08:51 +03:00
Maksim Shabunin
e0603bb45f Fixed several issues found by static analysis tools 2018-07-23 17:22:47 +03:00
Alexander Alekhin
ee743afebe dnn(ocl): don't use getUMat() for long live objects 2018-07-20 17:53:55 +03:00
Maksim Shabunin
a4060e15a4 dnn, IE backend: updated to match new interface 2018-07-19 19:22:23 +03:00
Dmitry Kurtaev
c213a3823e Run entire SSDs from TensorFlow using Intel's Inference Engine 2018-07-19 17:05:56 +03:00
Dmitry Kurtaev
070393dfda uint8 inputs for deep learning networks 2018-07-19 14:37:33 +03:00
Alexander Alekhin
6c4f618db5 Merge pull request #11104 from asciian:reading_from_stream 2018-07-17 16:24:06 +00:00
Maksim Shabunin
1da46fe6fb Fixed issues found by static analysis (mostly DBZ) 2018-07-17 16:14:54 +03:00
Alexander Alekhin
78d07e841d Merge pull request #11959 from pengli:3.4 2018-07-17 11:20:02 +00:00
Li Peng
f0cadaa6e3 enable concat layer fuse for OCL target 
Signed-off-by: Li Peng <peng.li@intel.com>
 2018-07-17 12:46:16 +08:00
Alexander Alekhin
c9439476da Merge pull request #11970 from dkurt:dnn_enable_tf_tests 2018-07-16 15:51:27 +00:00
Alexander Alekhin
d6c669f5cf Merge pull request #11963 from dkurt:dnn_cl_fix_matmul 2018-07-16 11:10:32 +00:00
Dmitry Kurtaev
6eb8faea85 Enable TensorFlow networks tests for different backends and targets 2018-07-13 19:58:56 +03:00
Dmitry Kurtaev
de6f0a537d Fix fully-connected layer in case of number of rows less than 4 2018-07-13 16:35:37 +03:00
Dmitry Kurtaev
dcc1beb1f8 Clip kernel for OpenCL PriorBox layer 2018-07-13 14:49:13 +03:00
Alexander Alekhin
2508f7f971 dnn(ocl): fix wrong usage of stalled .getMat() pointers 
Temporary object lifetime must be greater than pointer usage.
 2018-07-11 19:11:36 +03:00
Dmitry Kurtaev
8b5f061dae Replace std::vector<char> to std::vector<uchar> for Java bindings of dnn importers 2018-07-11 18:58:56 +03:00
Alexander Alekhin
999aba3807 Merge pull request #11936 from berak:dnn_shufflelayer_name 2018-07-11 12:01:31 +00:00
Li Peng
4c5a86828a Fix gemmlike convolution input reading 
use vload3 for half3 or float3 input vector reading,
also check read position to see if it exceed input width

Signed-off-by: Li Peng <peng.li@intel.com>
 2018-07-11 15:25:21 +08:00
berak
a7b502f04a dnn: preserve name, type strings for ShuffleLayer 2018-07-11 08:19:23 +02:00
Dmitry Kurtaev
d57e5406f0 Add readNet* functions which parse models from byte arrays 2018-07-10 11:12:01 +03:00
Alexander Alekhin
7fe0727930 Merge pull request #11924 from alalek:dnn_ocl_fix_max_pool_forward 2018-07-09 16:25:34 +00:00
Alexander Alekhin
b6255ab9e7 dnn(ocl4dnn): fix args for 'max_pool_forward' kernel 2018-07-09 18:02:20 +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
Dmitry Kurtaev
362d4f5395 Replace convertFp16 from dnn::Net::setInput() 2018-07-09 14:35:54 +03:00
asciian
61d8719b8d Reading net from std::ifstream 
Remove some assertions

Replace std::ifstream to std::istream

Add test for new importer

Remove constructor to load file

Rename cfgStream and darknetModelStream to ifile

Add error notification to inform pathname to user

Use FileStorage instead of std::istream

Use FileNode instead of FileStorage

Fix typo
 2018-07-09 10:02:05 +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
Alexander Alekhin
0bb2c115aa Merge pull request #11719 from alalek:update_autobuffer_api 2018-07-05 10:01:15 +00:00
Alexander Alekhin
ccd2370bb7 Merge pull request #11890 from dkurt:keras_resize_nearest 2018-07-05 09:57:24 +00:00
Alexander Alekhin
b09a4a98d4 opencv: Use cv::AutoBuffer<>::data() 2018-07-04 19:11:29 +03:00
Dmitry Kurtaev
f25a01bb5a Disable fusion to output layers 2018-07-04 15:53:47 +03:00
Dmitry Kurtaev
36288eebe7 Nearest neighbor resize from Keras 2018-07-04 11:53:24 +03:00
Dmitry Kurtaev
7ed5d85f25 Add Reshape layer tests 2018-07-03 08:26:43 +03:00
Alexander Alekhin
9be3f7d41a Merge pull request #11854 from dkurt:dnn_tf_data_layouts_v2 2018-06-29 15:02:22 +00:00
Alexander Alekhin
f40231af5d Merge pull request #11851 from pengli:3.4 2018-06-29 15:01:20 +00:00
Li Peng
145eae321e pooling ocl kernel optimization 
set global size with real output size, also optimize

max pooling index computation if necessary.

Signed-off-by: Li Peng <peng.li@intel.com>
 2018-06-29 15:22:49 +08:00
Dmitry Kurtaev
d971678add Add a planar data layout tracking for TensorFlow importer 2018-06-29 09:50:14 +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
dbeb4a11be Parse strides and convolution kernel shapes considering data layout 2018-06-26 16:18:21 +03:00
Vadim Pisarevsky
e87425f047 Merge pull request #11835 from dkurt:dnn_tf_two_inputs 2018-06-26 12:12:24 +00:00
Dmitry Kurtaev
9510551c63 Multiple inputs for TensorFlow models 2018-06-26 14:03:59 +03:00
Vadim Pisarevsky
b80c7bca0d Merge pull request #11826 from dkurt:dnn_tf_data_layouts 2018-06-26 06:36:27 +00:00
Dmitry Kurtaev
715f40a48d Use layers consumers to predict data layout 2018-06-25 18:25:40 +03:00
Li, Peng
ab8022f74e update convolution opencl kernels in dnn module (#11762) 
* optimize ocl kernel enqueue in fc layer

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

* use CV_LOG_INFO in convolution auto tuning

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

* update convolution IDLF kernel

extend parameter tuning range, also cleanup
ocl kernel implementation

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

* update in-memory convolution cache config

fp16 and fp32 cache config are stored separately

Signed-off-by: Li Peng <peng.li@intel.com>
 2018-06-25 17:06:18 +03:00
Dmitry Kurtaev
e8e9d1d021 Implement Interp layer using Resize layer 2018-06-22 19:26:47 +03:00
Alexander Alekhin
1894f1a37f Merge pull request #11773 from alalek:dnn_ocl_update_force_tuning_flag 2018-06-22 05:23:55 +00:00
Alexander Alekhin
50c607d206 dnn(ocl): fix external / predefined builtin configuration behavior 
OPENCV_OCL4DNN_FORCE_AUTO_TUNING should ignore existed configuration from:
- builtin predefined configurations (for Intel OpenCL iGPUs)
- external configuration (via OPENCV_OCL4DNN_CONFIG_PATH)

Prefer external configuration over builtin.
 2018-06-21 20:59:03 +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
Alexander Alekhin
30d4e0261a Merge pull request #11766 from dkurt:dnn_darknet_avgpool_softmax 2018-06-14 13:18:30 +00:00
Dmitry Kurtaev
bd87eb6e66 Import average pooling and softmax layers from Darknet 2018-06-14 15:22:08 +03:00
Dmitry Kurtaev
693a7663e7 Import ClipByValue from Keras 2018-06-14 13:30:30 +03:00
Alexander Alekhin
5fd7cfbcad dnn: add runtime parameter OPENCV_DNN_BACKEND_DEFAULT 
to control DNN_BACKEND_DEFAULT enumeration value behavior
 2018-06-13 19:00:04 +03:00
Alexander Alekhin
f040282bf8 Merge pull request #11739 from dkurt:more_ie_models 2018-06-13 13:26:50 +00:00
Dmitry Kurtaev
7d727ac2fb Fuse top layers to batch normalization 2018-06-09 18:06:53 +03:00
Dmitry Kurtaev
2c291bc2fb Enable FastNeuralStyle and OpenFace networks with IE backend 2018-06-09 15:57:12 +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
David
7175f257b5 Added ResizeBilinear op for tf (#11050) 
* Added ResizeBilinear op for tf

Combined ResizeNearestNeighbor and ResizeBilinear layers into Resize (with an interpolation param).

Minor changes to tf_importer and resize layer to save some code lines

Minor changes in init.cpp

Minor changes in tf_importer.cpp

* Replaced implementation of a custom ResizeBilinear layer to all layers

* Use Mat::ptr. Replace interpolation flags
 2018-06-07 16:29:04 +03:00
Dmitry Kurtaev
f3a6ae5f00 Wrap Inference Engine init to try-catch 2018-06-07 12:55:52 +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
Vadim Pisarevsky
055f33ec46 Merge pull request #11657 from dkurt:dnn_ie_multiple_networks 2018-06-04 10:12:46 +00:00
Kuang Fangjun
9ae28415ec fix doc. 2018-06-03 17:44:24 +08:00
Dmitry Kurtaev
ab389142af Fix multiple networks with Intel's Inference Engine backend 2018-06-01 14:10:32 +03:00
Alexander Alekhin
da75e463a8
Merge pull request #11639 from alalek:fix_precomp_hpp 2018-05-31 16:35:21 +00:00
Alexander Alekhin
799b4f48e7 fix missing precomp.hpp 2018-05-31 16:53:44 +03:00
Dmitry Kurtaev
32bab45f81 Fix Inference Engine graphs with fused output layers 2018-05-31 16:21:08 +03:00
Vadim Pisarevsky
c58cc4c2ff Merge pull request #11255 from dkurt:dnn_tf_faster_rcnn 2018-05-31 11:07:39 +00:00
Dmitry Kurtaev
f96f934426 Update Intel's Inference Engine deep learning backend (#11587) 
* Update Intel's Inference Engine deep learning backend

* Remove cpu_extension dependency

* Update Darknet accuracy tests
 2018-05-31 14:05:21 +03:00
Dmitry Kurtaev
bf87a43185 Faster-RCNN object detection models from TensorFlow 2018-05-30 17:12:36 +03:00
Alexander Alekhin
44572fac44 Merge pull request #11557 from tomoaki0705:relaxIntelOnlyOCL4DNN 2018-05-29 15:25:22 +00:00
Tomoaki Teshima
2e9e71ab9e make ocl4dnn available to run on other platform than Intel GPU 2018-05-29 19:18:10 +09:00
Dmitry Kurtaev
085be6a445 Fix dilated convolution from Keras 2018-05-29 12:15:47 +03:00
Dmitry Kurtaev
2c3c59d018 Remove Shift deep learning layer 2018-05-28 18:18:56 +03:00
Alexander Alekhin
3654fb10d7 Merge pull request #11567 from alalek:code_quality 2018-05-23 15:47:11 +00:00
Maksim Shabunin
895e10c317 dnn: fixed IE support on Windows 2018-05-23 12:46:14 +03:00
Alexander Alekhin
471c17321f improve code quality 
- eliminate rand() calls
- non initialized members/ variables
- unused return values
- missing/useless NULL checks
 2018-05-22 17:08:31 +03:00
Maksim Shabunin
53a68783a5 dnn: support later IE versions 2018-05-22 15:18:18 +03:00
Alexander Alekhin
085b27fc3d Merge pull request #11390 from dkurt:east_text_detection 2018-05-21 13:02:29 +00:00
Dmitry Kurtaev
07dc6d2b45 Return a convex hull from rotatedRectangleIntersection 2018-05-18 14:20:17 +03:00
Alexander Alekhin
d6279bfff8 fix build warnings 2018-05-17 18:29:21 +03:00
Li Peng
ba5e8befa9 fp16 ocl support for more layers 
Signed-off-by: Li Peng <peng.li@intel.com>
 2018-05-16 22:45:04 +08:00
Li Peng
3dd916882a fp16 ocl support for googlenet 
Signed-off-by: Li Peng <peng.li@intel.com>
 2018-05-16 22:45:02 +08:00
Li Peng
329abb5b64 dnn fp16 support 
Signed-off-by: Li Peng <peng.li@intel.com>
 2018-05-16 22:44:39 +08:00
Alexander Alekhin
bb8ff2c463 Merge pull request #11494 from tomoaki0705:fixOpenCLDnn 2018-05-16 14:11:36 +00:00
Tomoaki Teshima
3f5347dd7a work around of the test failure of opencv_test_dnn 
* let OpenCL kernel run only on Intel GPU
  * brush up the workaround based on 9a2b028 from alalek
 2018-05-16 19:23:19 +09:00
Dmitry Kurtaev
8488f2e265 EAST: An Efficient and Accurate Scene Text Detector (https://arxiv.org/abs/1704.03155v2) 2018-05-11 14:55:42 +03:00
Dmitry Kurtaev
c99c3e761e Fuse multipliers but not convolution layers weights 2018-05-10 19:24:38 +03:00
Dmitry Kurtaev
777d77848c Free Convolution and MatMul weights after TensorFlow layers import 2018-05-04 11:20:14 +03:00
Dmitry Kurtaev
9ffe4694db Reduce memory consumption at Caffe importer 2018-05-04 09:24:13 +03:00
zuoshaobo
4ff6a1bc7b Merge pull request #11425 from zuoshaobo:relu_negative_slope 
* FIX INF_ENGINE RELU ERROR

* set slope to variable

* tab in indentwq
 2018-05-03 13:36:49 +03:00
Alexander Alekhin
083b08742d Merge pull request #11406 from alalek:core_matsize_dims 2018-04-28 14:38:42 +00:00
Alexander Alekhin
65b0b319eb eliminate MSVS2017 build warning 
modules\dnn\src\layers\prior_box_layer.cpp(208): warning C4834: discarding return value of function with 'nodiscard' attribute
 2018-04-28 15:14:41 +03:00
Alexander Alekhin
8c349ff8ff core: added MatSize::dims() method 
to avoid accessing of 'p[-1]' (static code analysers dislike this)
 2018-04-27 16:57:29 +03:00
Alexander Alekhin
576d2dbac0 refactor: don't use CV_ErrorNoReturn() internally 2018-04-24 15:38:42 +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
Alexander Alekhin
29b4fd2774 Merge pull request #11351 from dkurt:dnn_enable_inf_engine_tests 2018-04-23 09:16:39 +00:00
Dmitry Kurtaev
d959d7b9f0 Fuse deconvolution layer subgraphs from Keras 2018-04-20 16:51:38 +03:00
Dmitry Kurtaev
bd77d100e1 Enable some tests for clDNN plugin from Intel's Inference Engine 2018-04-20 10:47:46 +03:00
Dmitry Kurtaev
3b4a292ca9 Let switch CPU/OpenCL targets for models from Intel's Model Optimizer 2018-04-19 10:23:57 +03:00
Vadim Pisarevsky
b290bdafb9 Merge pull request #11322 from dkurt:dnn_yolov3 2018-04-18 12:11:13 +00:00
Dmitry Kurtaev
66ce8cd7ea Fix bugs found by valgrind 2018-04-17 17:53:51 +03:00
Dmitry Kurtaev
97fec07d96 Support YOLOv3 model from Darknet 2018-04-16 18:44:12 +03:00
Alexander Alekhin
a2d6ee2d31 Merge pull request #11305 from tomoaki0705:typoNVIDIA 2018-04-13 12:56:42 +00:00
Tomoaki Teshima
a40354d16f use correct name for NVIDIA 
* remove NVidia and Nvidia
  * replace Cuda with CUDA
  * keep the letters for API
 2018-04-13 20:33:19 +09:00
Dmitry Kurtaev
b92c3182ab Blank and L2-normalization layers from Intel's Inference Engine 2018-04-12 15:21:08 +03:00
Vadim Pisarevsky
0b9d075958 Merge pull request #11295 from dkurt:dnn_repeated_conv_params 2018-04-11 15:25:24 +00:00
Vadim Pisarevsky
533bb89800 Merge pull request #11236 from dkurt:dnn_fuse_l2_norm 2018-04-11 15:09:55 +00:00
Vadim Pisarevsky
30175594e9 Merge pull request #11062 from dkurt:dnn_inf_engine_cldnn 2018-04-11 15:06:18 +00:00
Dmitry Kurtaev
512632e574 Parse repeated values of ConvolutionParameter 2018-04-11 14:38:05 +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
1ba72ca0d3 Fuse tf.nn.l2_normalize layer 2018-04-10 10:12:44 +03:00
Dmitry Kurtaev
709cf5d038 OpenCL GPU target for Inference Engine deep learning backend 
Enable FP16 GPU target for DL Inference Engine backend.
 2018-04-09 17:21:35 +03:00
Vladislav Sovrasov
0d9c63744e Add CPU default extensions loading in IE dnn backend (#11252) 
* Add CPU default extensions loading in IE dnn backend

* Load cpu_extensions for the future Intel's Inference Engine
 2018-04-09 16:22:19 +03:00
Dmitry Kurtaev
ef1aaf12c9 Fix Proposal deep learning layer 2018-04-04 14:48:29 +03:00
Dmitry Kurtaev
598039c0ed Fix embedded Torch's nn.ConcatTable 2018-03-31 11:11:10 +03:00
Alexander Alekhin
e8a67de0d2 Merge pull request #11182 from dkurt:fix_11102_part_2 2018-03-30 13:11:01 +00:00
Alexander Alekhin
1060c0f439 dnn: apply CV_OVERRIDE/CV_FINAL 2018-03-28 18:43:27 +03:00
Alexander Alekhin
167034fb04 Merge pull request #11098 from dkurt:dnn_native_inf_engine 2018-03-28 14:52:08 +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
2f3a9ba1d4 Update OpenCVDetectInferenceEngine.cmake 2018-03-28 16:34:37 +03:00
Alexander Alekhin
9e0dee1259 Merge pull request #11112 from alalek:cmake_src_include_fix 2018-03-27 13:06:48 +00:00
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
Alexander Alekhin
6c051a55e5 cmake: don't add include <module>/src directory to avoid conflicts 
during opencv_world builds
 2018-03-19 11:14:15 +03:00
Dmitry Kurtaev
069f9add80 Fix an issue https://github.com/opencv/opencv/issues/11102 2018-03-18 10:49:12 +03:00
Alexander Alekhin
d68466bb6a Merge pull request #10940 from dkurt:dnn_tf_graph_optim 2018-03-14 14:36:25 +00:00
Alexander Alekhin
ab110c0ad1 Merge pull request #10979 from dkurt:unite_dnn_samples 2018-03-14 14:33:49 +00:00
Dmitry Kurtaev
538fd42363 Add test for Scalar arguments at CommandLineParser 2018-03-13 11:01:07 +03:00
Dmitry Kurtaev
ab20d2a3fc Update assertions in batch norm layer 2018-03-12 10:53:06 +03:00
Dmitry Kurtaev
69a8f110b6 Fuse subgraphs from Keras 2018-03-12 10:53:06 +03:00
Dmitry Kurtaev
9457bf10ab Fuse batch normalization and flatten TensorFlow subgraphs in runtime 2018-03-12 10:51:35 +03:00
Alexander Alekhin
5b868ccd82 Merge pull request #10992 from dkurt:dnn_opencl_tests 2018-03-09 10:06:40 +00:00
Dmitry Kurtaev
0f01b40dd5 Reset OpenCL kernels if batch size changes 2018-03-07 17:06:59 +03:00
Alexander Alekhin
514f4193db Merge pull request #10959 from alalek:cmake_ocl4dnn 2018-03-07 10:26:14 +00:00
Dmitry Kurtaev
e1c3237532 Parametric OpenCL deep learning tests 2018-03-05 20:53:18 +03:00
Dmitry Kurtaev
f2440ceae6 Update tutorials. A new cv::dnn::readNet function 2018-03-04 20:30:22 +03:00
Alexander Alekhin
fe97dc67dc Merge pull request #10962 from alalek:dnn_precomp_hpp 2018-03-02 11:38:16 +00:00
Alexander Alekhin
97c1f09961 Merge pull request #10955 from pengli:dnn 2018-03-02 11:35:59 +00:00
Alexander Alekhin
a9ebc61f2a dnn(workaround): switch to CPU target if compiled without OpenCL 2018-03-01 12:12:40 +03:00
Alexander Alekhin
1b83bc48a1 dnn: make OpenCL DNN code optional 2018-03-01 12:12:40 +03:00
Alexander Alekhin
a838a97092 dnn: fix precomp.hpp usage 2018-02-28 17:06:26 +03:00
Wu Zhiwen
ef937dd676 ocl4dnn: Fix SAME padding mode for convolve 
Signed-off-by: Wu, Zhiwen <zhiwen.wu@intel.com>
Signed-off-by: Li Peng <peng.li@intel.com>
 2018-02-28 21:02:41 +08:00
Maksim Shabunin
7c855aa3e1 Fixed two issues found by static analysis 2018-02-26 00:16:02 +03:00
Li Peng
608968aa83 Deconvolution ocl fix 
Signed-off-by: Li Peng <peng.li@intel.com>
 2018-02-23 18:31:30 +08:00
Li, Peng
5caf6244a3 Merge pull request #10922 from pengli:dnn 
* ave pooling ocl fix

support the padded area control in ave pooling

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

* warning fix: ununitialized field
 2018-02-22 21:01:12 +03:00
Maksim Shabunin
92e9d4ec3a Fixed several issues detected by static analysis 2018-02-22 17:11:33 +03:00
Vadim Pisarevsky
5e0f95b948 Merge pull request #9708 from dkurt:tf_face_detector 2018-02-22 12:04:26 +00:00
Li Peng
e7d35d51fa Fix for opencv face detector ocl test 
Signed-off-by: Li Peng <peng.li@intel.com>
 2018-02-22 23:37:54 +08:00
Li Peng
c524f669c7 Fallback for "SAME" padMode in ocl convolution and pooling 
It fixes tensorflow ocl testcase of MobileNetSSD and Inception_v2_SSD

Signed-off-by: Li Peng <peng.li@intel.com>
 2018-02-22 21:17:59 +08:00
Dmitry Kurtaev
eab556e1e0 OpenCV face detection network in TensorFlow 2018-02-21 19:58:24 +03:00
Alexander Alekhin
53305d4a7e Merge pull request #10891 from pengli:dnn 2018-02-20 08:59:07 +00:00
Li Peng
2863f950d6 ReLU6 layer ocl support 
include relu6 ocl kernel and layer fusion support

Signed-off-by: Li Peng <peng.li@intel.com>
 2018-02-20 15:11:09 +08:00
Dmitry Kurtaev
8b4871a28d Use only absolute prior boxes explicit sizes. Remove scales attributes. (#10874) 
* Use only absolute prior boxes explicit sizes. Remove scales attributes.

* Simplified PriorBox layer forward pass
 2018-02-19 17:25:18 +03:00
Alexander Alekhin
0e4eed0ba1 Merge pull request #10867 from dkurt:dnn_fix_ave_pooling_area 2018-02-16 11:17:32 +00:00
Alexander Alekhin
c020a7bb67 build: portable integer types 2018-02-15 23:43:02 +03:00
Dmitry Kurtaev
f8d0d6365e Add a flag to manage average pooling with padding 2018-02-14 16:56:31 +03:00
Alexander Alekhin
cff79609c8 Merge pull request #10854 from pengli:dnn 2018-02-14 12:49:53 +00:00
Vadim Pisarevsky
ef70b0baa4 Merge pull request #10865 from dkurt:dnn_inf_engine_getInputsInfo 2018-02-14 12:25:18 +00:00
Dmitry Kurtaev
a66b5e2c13 Add const getInputsInfo 2018-02-14 14:17:44 +03:00
Vadim Pisarevsky
6dfd7e3da2 Merge pull request #10850 from dkurt:dnn_tf_deconv_tests 2018-02-14 10:35:14 +00:00
Li Peng
5992c46606 add fallback case for ocl convolution 
The ocl convolution doesn't support tensorflow padMode well.
Add fallback check if we meet this situation, it could fix the
tensorflow MobileNet SSD failure.

Signed-off-by: Li Peng <peng.li@intel.com>
 2018-02-14 00:04:38 +08:00
Li Peng
00d2f34888 ocl fix for detection_output and prior_box layer 
Signed-off-by: Li Peng <peng.li@intel.com>
 2018-02-13 23:09:14 +08:00
Dmitry Kurtaev
514e6df460 Refactored deep learning layers fusion 2018-02-13 14:35:58 +03:00
Dmitry Kurtaev
a6baedd02c Fix deconvolution layer. Add batch norm layer with mean-variance normalization from TensorFlow. 2018-02-13 11:00:27 +03:00
Alexander Alekhin
66f3c1ae79 Merge pull request #10843 from luzpaz:misc-modules-typos 2018-02-12 13:47:12 +00:00
Sui Libin
1ad814a191 fix faster_rcnn sample crashed at PoolingInvoker on Windows7(x64). (#10724) 
* fix faster_rcnn sample crashed at PoolingInvoker operator() of pooling_layer.

* find_odj onmouse bug about find matched point status.

* reverted AutoBuffer back to std::vector
 2018-02-12 16:07:56 +03:00
luz.paz
5718d09e39 Misc. modules/ typos 
Found via `codespell`
 2018-02-12 07:09:43 -05:00
Rémi Ratajczak
b67523550f dnn : Added an imagesFromBlob method to the dnn module (#10607) 
* Added the imagesFromBlob method to the dnn module.

* Rewritten imagesFromBlob based on first dkurt comments

* Updated code with getPlane()

* Modify comment of imagesFromBlob() in dnn module

* modified comments, removed useless assertions & added OutputArrayOfArray

* replaced tabs with whitespaces & put vectorOfChannels instantiation outside the loop

* Changed pre-commit.sample to pre-commit in .git/hooks/

* Added a test for imagesFromBlob in test_misc.cpp (dnn)

* Changed nbOfImages, robustified test with cv::randu, modified assertion
 2018-02-12 14:51:07 +03:00
Dmitry Kurtaev
7fe97376c2 MobileNet-SSD from TensorFlow 1.3 and Inception-V2-SSD using Inference Engine backend 2018-02-09 13:45:45 +03:00
Dmitry Kurtaev
ed94136548 OpenCV face detection network using Inference Engine backend 2018-02-06 17:53:24 +03:00
Alexander Alekhin
398ebbac98 Merge pull request #10795 from pengli:dnn 2018-02-06 10:04:29 +00:00
Li Peng
c43498c6ad check vector emptiness before access it 
Signed-off-by: Li Peng <peng.li@intel.com>
 2018-02-06 22:59:51 +08:00
Li Peng
389fa5d38e slice layer ocl update 
Signed-off-by: Li Peng <peng.li@intel.com>
 2018-02-06 22:59:47 +08:00
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
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
Vadim Pisarevsky
713ec7be45 Merge pull request #10746 from dkurt:dnn_batch_norm_from_nvidia_caffe 2018-02-01 13:22:09 +00:00
Alexander Alekhin
42569cfd61 Merge pull request #10748 from dkurt:fix_dnn_slice_layer 2018-02-01 13:21:17 +00:00
Alexander Alekhin
9d25bd583f Merge pull request #10754 from dkurt:dnn_ocl_gemv_min_globalsize 2018-02-01 12:39:27 +00:00
Dmitry Kurtaev
65a6674c6e ocl4dnnGEMV in case of row_size < 4 2018-02-01 14:06:47 +03:00
Alexander Alekhin
9698b93d10 Merge pull request #10717 from pengli:dnn 2018-02-01 10:49:54 +00:00
Li Peng
6aec71d7ee mvn layer ocl update 
it fuse ocl kernels to reduce kernel enqueue

Signed-off-by: Li Peng <peng.li@intel.com>
 2018-02-01 17:48:12 +08:00
Li Peng
83b16ab7b7 fix extra spaces in build option 
Signed-off-by: Li Peng <peng.li@intel.com>
 2018-02-01 17:46:11 +08:00
Li Peng
54c81cbde4 eltwise layer SUM op update 
Signed-off-by: Li Peng <peng.li@intel.com>
 2018-02-01 17:46:06 +08:00
Dmitry Kurtaev
184862582c Fix slice layer from TensorFlow 2018-01-31 19:12:37 +03:00
Arjan van de Ven
a75840d19c Merge pull request #10468 from fenrus75:avx512-2 
* Add a 512 bit codepath to the AVX512 fastConv function

this patch adds a 512 wide codepath to the fastConv() function for
AVX512 use.
The basic idea is to process the first N * 16 elements of the vector
with avx512, and then run the rest of the vector using the traditional
AVX2 codepath.

* dnn: use unaligned AVX512 load (OpenCV aligns data on 32-byte boundary)

* dnn: change "vecsize" condition for AVX512

* dnn: fix indentation
 2018-01-31 16:34:12 +03:00
Alexander Alekhin
f06c44f1f1 Merge pull request #10701 from dkurt:tf_ave_pooling 2018-01-31 13:28:09 +00:00
Dmitry Kurtaev
844f1d0281 Fix Batch Normalization layer imported from NVIDIA Caffe. 2018-01-31 16:25:45 +03:00
Dmitry Kurtaev
a2e9bfbaf4 Fix padding for average pooling from TensorFlow 2018-01-31 15:54:30 +03:00
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
2876670de3 dnn(ocl): fix build options for Apple OpenCL 2018-01-28 01:54:25 +00:00
Alexander Alekhin
104502c5be Merge pull request #10676 from dkurt:dnn_for_newer_mobilenet_ssd 2018-01-26 04:02:21 +00:00
Li Peng
2493083935 mvn, batch_norm and relu layer fusion 
Signed-off-by: Li Peng <peng.li@intel.com>
 2018-01-25 18:57:05 +08:00
Li Peng
e15928b49e convolution and tanh layer fusion 
Signed-off-by: Li Peng <peng.li@intel.com>
 2018-01-25 17:45:33 +08:00
Dmitry Kurtaev
9e9926a2f0 PriorBox layer with explicit normalized sizes 2018-01-24 14:01:42 +03:00
Dmitry Kurtaev
a3d74704e5 OpenCV face detection network test 2018-01-23 09:27:58 +03:00
Alexander Alekhin
26e0f408f0 Merge pull request #10639 from pengli:dnn 2018-01-19 10:01:41 +00:00
Li Peng
fe494297e4 more update on MVN layer ocl implementation 
cut one ocl kernel if normVariance is disabled,
also use native_powr for performance reason.

Signed-off-by: Li Peng <peng.li@intel.com>
 2018-01-19 22:54:04 +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
Li Peng
4189214d04 batch_norm layer ocl update 
use a batch_norm ocl kernel to do the work

Signed-off-by: Li Peng <peng.li@intel.com>
 2018-01-16 19:01:58 +08:00
Alexander Alekhin
1255bd8d4b Merge pull request #10585 from dkurt:dnn_weightless_scale 2018-01-15 06:07:50 +00:00
Dmitry Kurtaev
6a395d88ff dnn::blobFromImage with OutputArray 2018-01-13 18:20:24 +03:00
Dmitry Kurtaev
1f4fdfd599 Untrainable version of Scale layer from Caffe 2018-01-13 10:35:29 +03:00
Dmitry Kurtaev
64a9e92390 Merge pull request #10466 from dkurt:reduce_umat_try_2 
* UMat blobs are wrapped

* Replace getUMat and getMat at OpenCLBackendWrapper
 2018-01-10 21:50:54 +03:00
Alexander Alekhin
4d4f291553 Merge pull request #10513 from pengli:dnn 2018-01-09 19:24:28 +00:00
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
Alexander Alekhin
da0904df2d Merge pull request #10550 from dkurt:replace_psroi_pooling_tag 2018-01-08 19:19:00 +00:00
Dmitry Kurtaev
27b55ea761 Replace Caffe's psroi_pooling_param tag from 10001 to 10002 2018-01-08 13:29:20 +03:00
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
Arthur Williams
8a67858068 Fixed missing #include "../precomp.hpp" 2018-01-05 15:10:39 +00:00
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
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
Li Peng
34bfd7ef51 add ocl implementation of proposal layer 
Signed-off-by: Li Peng <peng.li@intel.com>
 2018-01-04 18:40:51 +08:00
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
a65b5df5da Merge pull request #10416 from fenrus75:avx512 2017-12-28 15:56:56 +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
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
99a9c10b57 Merge pull request #10424 from dkurt:fix_concat_optim 2017-12-28 01:26:14 +00:00
Alexander Alekhin
f3880c60a6 Merge pull request #10428 from pengli:dnn 2017-12-27 13:18:10 +00:00
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
70c605a03d Limit Concat layer optimization 2017-12-26 16:49:33 +03:00
Li Peng
84e2fa79a0 dnn(ocl4dnn): update pre-tuned kernel config 
Signed-off-by: Li Peng <peng.li@intel.com>
 2017-12-26 20:14:41 +08:00
Alexander Alekhin
adf43e7d2a build: fix MSVS2010 build error 2017-12-23 00:06:34 +00:00
Alexander Alekhin
019b7c5a66 Merge pull request #10402 from dkurt:dnn_tf_quantized 2017-12-22 15:58:56 +00:00
Alexander Alekhin
59e825ee02 Merge pull request #10385 from pengli:dnn 2017-12-22 15:48:40 +00:00
Dmitry Kurtaev
bcc669f3f7 TensorFlow weights dequantization 2017-12-22 17:25:10 +03:00
Alexander Alekhin
97af608030 Merge pull request #10397 from mshabunin:fix-incorrect-assert 2017-12-22 14:07:02 +00:00
Li Peng
181b448c4d add one more convolution kernel tuning candidate 
Signed-off-by: Li Peng <peng.li@intel.com>
 2017-12-22 21:37:00 +08:00
Vadim Pisarevsky
0742e12f0b Merge pull request #10265 from dkurt:nms_for_region_layer 2017-12-22 13:29:37 +00:00
Maksim Shabunin
aa46e31c6d Replaced incorrect CV_Assert calls with CV_Error 2017-12-22 15:20:13 +03:00
Vadim Pisarevsky
325cbd7c84 Merge pull request #10364 from dkurt:dnn_smooth_tf_data_layout 2017-12-22 09:56:45 +00:00
Li Peng
c5fc8e03ff cleanup unnecessary macros in convolution ocl kernel 
Signed-off-by: Li Peng <peng.li@intel.com>
 2017-12-21 20:32:36 +08:00
Li Peng
0aa5e43a14 refactor candidate generation of convolution auto-tuning 
Signed-off-by: Li Peng <peng.li@intel.com>
 2017-12-21 23:05:54 +08:00
Dmitry Kurtaev
c67e75b68f Refactor NMS procedure at RegionLayer 2017-12-21 12:21:45 +03:00
Dmitry Kurtaev
7e48fa58eb Manage TensorFlow's NHWC data layout is smoother 2017-12-20 14:13:40 +03:00
Dmitry Kurtaev
0ed2cbc931 R-FCN models support 2017-12-20 10:43:22 +03:00
Alexander Alekhin
dcdd6af5a8 Merge pull request #10341 from pengli:dnn 2017-12-19 14:04:55 +00:00
Li Peng
436d7e4eaf add depthwise convolution kernel 
Signed-off-by: Li Peng <peng.li@intel.com>
 2017-12-19 17:59:13 +08:00
Li Peng
910d7dab1f prior box layer ocl implementation 
Signed-off-by: Li Peng <peng.li@intel.com>
 2017-12-19 17:44:10 +08:00
Dmitry Kurtaev
6aabd6cc7a Remove cv::dnn::Importer 2017-12-18 18:08:28 +03:00
Dmitry Kurtaev
2b43d4f477 Fix default pooling layer type 2017-12-17 16:46:40 +03:00
Maksim Shabunin
1033f2b1bd Fixed 3 issues found by static analysis 2017-12-15 17:29:26 +03:00
Vadim Pisarevsky
62359f70ff Merge pull request #10306 from dkurt:faster_rcnn 2017-12-15 12:23:53 +00:00
Dmitry Kurtaev
08112f3821 Faster-RCNN models support 2017-12-15 12:16:21 +03:00
Alexander Alekhin
0da947e6b3 dnn: more debug information 2017-12-14 19:21:17 +03:00
Alexander Alekhin
c231472ad6 Merge pull request #10290 from tomoaki0705:fixVS2012Round 2017-12-13 15:30:21 +00:00
Tomoaki Teshima
ecb6bcf2e0 fix build error on Visual Studio 2012 
* round doesn't exists in standard library of Visual Studio 2012
  * apply the correct computation of ROI
 2017-12-13 17:40:07 +03:00
Vitaly Tuzov
51cb56ef2c Implementation of bit-exact resize. Internal calls to linear resize updated to use bit-exact version. (#9468) 2017-12-13 15:00:38 +03:00
Alexander Alekhin
eff42f6387 dnn: more debug info 2017-12-12 12:04:10 +03:00
Vadim Pisarevsky
7e680bd9ff Merge pull request #10215 from dkurt:dnn_js 2017-12-11 12:47:52 +00:00
Vadim Pisarevsky
c24f10d647 Merge pull request #10268 from dkurt:fix_scale_layer 2017-12-08 18:46:50 +00:00
Dmitry Kurtaev
f503515082 JavaScript bindings for dnn module 2017-12-08 18:33:48 +03:00
Dmitry Kurtaev
e307065c8e Scale layer in case of 2D inputs 2017-12-08 17:34:59 +03:00
Alexander Alekhin
f2070c9f5d Merge pull request #10255 from dkurt:dnn_roi_pooling 2017-12-08 11:20:07 +00:00
Dmitry Kurtaev
17dcf0e82d ROIPooling layer 2017-12-07 19:04:38 +03:00
Dmitry Kurtaev
ef0650179b Fix conv/deconv/fc layers FLOPS computation 2017-12-07 11:42:04 +03:00
Alexander Alekhin
6074f92d48 Merge pull request #10228 from pengli:dnn_new 2017-12-06 15:50:12 +00:00
Li Peng
59cbaca4d3 detection_output layer ocl implementation 
Signed-off-by: Li Peng <peng.li@intel.com>
 2017-12-06 22:35:59 +08:00
Li Peng
66feea6cac region layer ocl implementation 
Signed-off-by: Li Peng <peng.li@intel.com>
 2017-12-07 02:26:46 +08:00
Li Peng
7707c9bfba reorg layer ocl implementation 
Signed-off-by: Li Peng <peng.li@intel.com>
 2017-12-07 02:26:46 +08:00
Li Peng
85b1c4060c support axis in concat layer ocl path 
Signed-off-by: Li Peng <peng.li@intel.com>
 2017-12-07 02:26:46 +08:00
Li Peng
07bec6bdcd reshape layer ocl implementation 
Signed-off-by: Li Peng <peng.li@intel.com>
 2017-12-07 02:26:40 +08:00
Li Peng
7b7033ac60 permute layer ocl implementation 
Signed-off-by: Li Peng <peng.li@intel.com>
 2017-12-05 22:10:05 +08:00
Dmitry Kurtaev
bbbec300a6 nn.BatchNormalization and nn.Dropout layers from Torch 2017-12-04 12:57:21 +03:00
Alexander Alekhin
cc2ee923e4 Merge pull request #10164 from pengli:dnn 2017-11-29 12:05:10 +00:00
Wu Zhiwen
1f465a0ef9 dnn(ocl4dnn): fuseLayer() use umat_input/outputBlobs for OpenCL target 
Also, fix bug when use OPENCL target but no OpenCL runtime

Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com>
 2017-11-27 22:25:53 +08:00
Dmitry Kurtaev
99ed085752 Update PriorBox layer 2017-11-27 16:47:20 +03:00
Alexander Alekhin
13f374660f dnn(ocl4dnn): drop unused batch_size_ in pooling 2017-11-23 20:46:56 +00:00
Alexander Alekhin
e34b64c979 dnn(ocl4dnn): refactor pooling OpenCL calls 2017-11-23 20:46:44 +00:00
Alexander Alekhin
f071a48ec7 Merge pull request #10143 from pengli:ocl4dnn 2017-11-23 18:47:14 +00:00
Alexander Alekhin
107582c767 Merge pull request #9996 from dkurt:dnn_multiple_inputs 2017-11-23 18:22:37 +00:00
Li Peng
636d6368ee use OutputArrayOfArrays in net forward interface 
It allows umat buffers used in net forward interface

Signed-off-by: Li Peng <peng.li@intel.com>
 2017-11-24 02:19:10 +08:00
Wu, Zhiwen
04edc8fe3a cleanup ocl4dnn spatial convolution kernels 
remove unused macros and half definition macros,
also remove unused ocl::Queue

Signed-off-by: Li Peng <peng.li@intel.com>
 2017-11-24 02:19:10 +08:00
Alexander Alekhin
49a5280198 Merge pull request #10139 from alalek:dnn_rename_caffe_proto_package 2017-11-23 14:10:42 +00:00
Alexander Alekhin
f37f4cf3b4 Merge pull request #9994 from r2d3:dnn_memory_load 2017-11-22 18:15:00 +00:00
Alexander Alekhin
e7d62d6ef3 Merge pull request #10126 from alalek:dnn_issue_10125 2017-11-22 18:03:51 +00:00
Alexander Alekhin
1c88a566e0 dnn: rename caffe protobuf package 2017-11-22 18:34:07 +03:00
Alexander Alekhin
9db5cbf9a4 dnn: sync output/internals blobs back 2017-11-22 14:00:58 +03:00
Vadim Pisarevsky
f8ad289311 Merge pull request #10092 from alalek:dnn_rename_caffe_proto 2017-11-22 08:16:20 +00:00
Alexander Alekhin
0f34628af7 dnn: drop OpenCL code path for DetectionOutputLayer 
getUMat()/getMat() calls are scope based. Results of these calls can't be
stored somewhere for future usage.
 2017-11-21 17:28:42 +03:00
Alexander Alekhin
438e456ce9 Merge pull request #10113 from wzw-intel:fusion 2017-11-20 18:13:33 +00:00
Alexander Alekhin
f6d927ef3b dnn: avoid conflicts with original caffe.proto 
rename caffe.proto => opencv-caffe.proto
 2017-11-20 19:04:00 +03:00
David Geldreich
f723cede2e add loading TensorFlow/Caffe net from memory buffer 
add a corresponding test
 2017-11-20 16:28:22 +01:00
Dmitry Kurtaev
6c5dd5cf6d Replace caffe::NormalizedBBox to local structure 2017-11-20 18:03:31 +03:00
Wu Zhiwen
45d11dde57 dnn(ocl4dnn): add fusion support for Power activation and eltwise add 
Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com>
 2017-11-20 14:58:53 +08:00
Wu Zhiwen
394101d6ed dnn(ocl4dnn): Fix relu fusion bug 
Incorrect type of negative_slope result in this bug.

Also and OCL test for darknet to validate this patch.

Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com>
 2017-11-17 16:21:56 +08:00
Wu Zhiwen
88e6daa315 dnn(ocl4dnn): Fix wrong measurement for tuning time 
convolution kernel use default queue to run, so that ocl::Timer
, to measure the kernel run time, should use the default queue too.
Also remove useless parameter for convolve()

Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com>
 2017-11-16 13:09:57 +08:00
Li Peng
55260a8d3c reshape mat before doing computation in fc layer 
Signed-off-by: Li Peng <peng.li@intel.com>
 2017-11-13 09:29:50 +08:00
Alexander Alekhin
bafdc44d37 Merge pull request #10061 from Sahloul:dnn_torch_fix 2017-11-10 05:05:52 +00:00
Alexander Alekhin
8a3a75cc16 Merge pull request #9882 from pengli:ocl4dnn 2017-11-09 18:54:43 +00:00
Hamdi Sahloul
06bda58a2c DNN Torch - workaround when torch importer is disabled 2017-11-10 00:44:06 +09:00
Li Peng
8f99083726 Add new layer forward interface 
Add layer forward interface with InputArrayOfArrays and
OutputArrayOfArrays parameters, it allows UMat buffer to be
processed and transferred in the layers.

Signed-off-by: Li Peng <peng.li@intel.com>
 2017-11-09 15:59:39 +08:00
Alexander Alekhin
97181a90ba dnn(ocl4dnn/conv): bailout on missing kernel configuration 2017-11-07 17:02:17 +03:00
Alexander Alekhin
6e4f9433d0 Merge pull request #9998 from alalek:ocl_fix_dnn_softmax_9991 2017-11-03 09:16:39 +00:00
Dmitry Kurtaev
20a2dc6ac5 Fix multiple inputs models from Caffe. 
Fixed Concat optimization.
 2017-11-02 18:55:08 +03:00
Alexander Alekhin
bacc96f4e8 dnn(ocl): fix softmax global/local size consistency 2017-11-02 17:08:40 +03:00
Dmitry Kurtaev
14af2a0c0c Fixed Halide's copy_to_device invocation 2017-11-01 14:01:54 +03:00
Vadim Pisarevsky
bc348eb8ab Merge pull request #9963 from dkurt:fix_caffe_shrinker 2017-10-31 12:27:19 +00:00
Dmitry Kurtaev
e1ebc4e991 Specify layer types for Caffe FP32->FP16 weights converter 2017-10-31 12:31:40 +03:00
Dmitry Kurtaev
03cefa7bfe Set zero confidences in case of no detections 2017-10-30 10:17:57 +03:00
Vadim Pisarevsky
e0e40405ed Merge pull request #9847 from wzw-intel:ocl4dnn_fusion 2017-10-27 13:59:46 +00:00
Vadim Pisarevsky
ff037ebe5f Merge pull request #9845 from dkurt:fast_neural_style_models 2017-10-27 13:59:02 +00:00
Vadim Pisarevsky
5384d2f090 Merge pull request #9880 from dkurt:caffe_ceil_mode 2017-10-27 11:51:46 +00:00
Dmitry Kurtaev
4b52b8df34 Layers for fast-neural-style models: https://github.com/jcjohnson/fast-neural-style 2017-10-27 14:26:45 +03:00
Vadim Pisarevsky
bc93775385 Merge pull request #9862 from sovrasov:dnn_nms 2017-10-27 11:19:57 +00:00
Vadim Pisarevsky
825c0ffdb4 Merge pull request #9874 from dkurt:fix_identity_permute_layer 2017-10-27 11:11:48 +00:00
Vadim Pisarevsky
69f2590359 Merge pull request #9921 from dkurt:fix_prelu_after_fully_connected 2017-10-27 11:10:59 +00:00
Vadim Pisarevsky
7b8fb64f21 Merge pull request #9939 from alalek:fix_dnn_getUMat_crash 2017-10-27 11:06:22 +00:00
Vladislav Sovrasov
5bf39ceb5d dnn: handle 4-channel images in blobFromImage (#9944) 2017-10-27 14:06:53 +03:00
Alexander Alekhin
436a1f72a5 dnn: fix sporadic crashes in getUMat() 
Incorrect "total" buffer size calculated in StdMatAllocator::allocate() due wrong step values.
 2017-10-25 18:07:05 +03:00
Vladislav Sovrasov
7e3e9144de dnn: add an accuracy test for NMS 2017-10-25 13:40:56 +03:00
Vladislav Sovrasov
c704942b8a dnn: add a documentation for NMS, fix missing experimantal namespace 2017-10-25 13:35:49 +03:00
Vladislav Sovrasov
acedb4a579 dnn: make NMS function public 2017-10-25 13:35:49 +03:00
Dmitry Kurtaev
a36ebaecdc PReLU layer for multidimensional input 2017-10-23 16:13:03 +03:00
Alexander Alekhin
185faf99bd ocl: simplify ocl::Timer interface 2017-10-18 16:01:21 +03:00
Dmitry Kurtaev
b903ff8992 Ceil mode from experimental version of Caffe, https://github.com/BVLC/caffe/pull/3057 2017-10-18 14:04:53 +03:00
Dmitry Kurtaev
a3a446c197 Output blobs shapes initialization in case of identity permutation (NCHW->NCHW) 2017-10-17 17:15:25 +03:00
Wu Zhiwen
2d8f2c2aea dnn(ocl4dnn): add fusion support 
ocl4dnn supports following fusion styles:
Conv + [BN] + [Scale] + [ReLU/PReLU]

Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com>
 2017-10-16 19:18:36 +08:00
Maksim Shabunin
b066dd36ff Fixed uninitialized class fields 2017-10-16 13:47:43 +03:00
Alexander Alekhin
4857cae6ed dnn: don't use "experimental_dnn_v1" namespace directly 2017-10-12 18:16:53 +03:00
Alexander Alekhin
df5b2224d7 Merge pull request #9829 from pengli:ocl4dnn 2017-10-12 11:26:20 +00:00
Li Peng
937b8e4277 dnn(ocl4dnn): support log softmax in ocl4dnn 
Signed-off-by: Li Peng <peng.li@intel.com>
 2017-10-12 09:51:13 +08:00
Vadim Pisarevsky
e356ca2369 Merge pull request #9835 from sovrasov:blob_from_img_crop_opt 2017-10-11 17:18:40 +00:00
Vadim Pisarevsky
8b168175ec Merge pull request #9636 from dkurt:duplicate_lp_norm_layer 2017-10-11 13:36:14 +00:00
Vadim Pisarevsky
0873ebb9b0 Merge pull request #9820 from sovrasov:text_detector_dnn 2017-10-11 13:31:46 +00:00
Vadim Pisarevsky
babd21c764 Merge pull request #9823 from alalek:dnn_halide_bypass_tbb_threads 2017-10-11 13:28:38 +00:00
Vladislav Sovrasov
47e1133e71 dnn: add crop flag to blobFromImage 2017-10-11 15:46:20 +03:00
Vladislav Sovrasov
f7175f5050 dnn: fix additional text boxes handling after the latest adaptations for TF 2017-10-11 14:04:48 +03:00
Vladislav Sovrasov
050916fd6b dnn: modify priorBox layer 2017-10-11 11:43:50 +03:00
Dmitry Kurtaev
905a9dada2 Removed LPNormalize layer. 2017-10-10 20:38:55 +03:00
Alexander Alekhin
3935e13603 dnn(halide): don't compile Halide via parallel_for_() 
To avoid problem with reduced stack size of inner threads.
 2017-10-10 18:06:03 +03:00
Vadim Pisarevsky
b7ff9ddcdd Merge pull request #9705 from AlexeyAB:dnn_darknet_yolo_v2 2017-10-10 12:02:03 +00:00
Vadim Pisarevsky
046045239c Merge pull request #9750 from dkurt:feature_dnn_tf_text_graph 2017-10-10 10:06:24 +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
Vadim Pisarevsky
fee87ea3f7 Merge pull request #9800 from alalek:fix_build_msvs2010 2017-10-09 12:33:08 +00:00
Vadim Pisarevsky
6a80834ed4 Merge pull request #9803 from wzw-intel:ocl_timer 2017-10-09 12:11:22 +00:00
Maksim Shabunin
5a22d81fe5 Fixed warnings produced by static analyzer 2017-10-09 13:37:18 +03:00
Wu Zhiwen
dbe9ee0924 ocl: simplify ocl::Timer 
Use clFinish to gurantee commands completed, instead of waiting for events.

Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com>
 2017-10-09 13:48:38 +08:00
Alexander Alekhin
e615fafe2d build: fix MSVS2010 2017-10-08 23:32:22 +03:00
Dmitry Kurtaev
e4aa39f9e5 Text TensorFlow graphs parsing. MobileNet-SSD for 90 classes. 2017-10-08 22:25:29 +03:00
Vadim Pisarevsky
21bd834a59 Merge pull request #9772 from dkurt:fix_caffe_eltwise_and_fc_layers 2017-10-06 13:47:54 +00:00
Vadim Pisarevsky
b969d86415 Merge pull request #9787 from dkurt:feature_dnn_resize_nearest_neighbor 2017-10-06 13:46:50 +00:00
Vadim Pisarevsky
fe58b58937 Merge pull request #9778 from dkurt:dnn_colorization 2017-10-06 11:48:05 +00:00
Dmitry Kurtaev
b9f94c9315 Nearest neighbor resize layer 2017-10-06 14:33:26 +03:00
Dmitry Kurtaev
e268606e26 Grayscale colorization model (https://github.com/richzhang/colorization) test. 2017-10-06 09:33:41 +03:00
Dmitry Kurtaev
ad8bbaf008 Multidimensional eltwise layer. 
Fixed fully-connected layer axis.
 2017-10-04 14:01:44 +03:00
Dmitry Kurtaev
2a21c10837 Fix TensorFlow split layer 2017-10-02 22:44:42 +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
Vadim Pisarevsky
5e93c82023 Merge pull request #9491 from dkurt:tf_lstm 2017-09-28 21:04:06 +00:00
Vadim Pisarevsky
68cc2e292d Merge pull request #9734 from dkurt:fix_deconv_layer_kernel_layout 2017-09-28 11:42:57 +00:00
Vadim Pisarevsky
45365e4df1 Merge pull request #9691 from dkurt:padding_layer_refactoring 2017-09-28 11:34:28 +00:00
Dmitry Kurtaev
6e593cd1f0 Swap dimensions of deconvolution kernel 2017-09-27 22:38:34 +03:00
Alexander Alekhin
3dee92ec50 fix usage of CV_FMA3 macro 2017-09-26 17:23:54 +03:00
Dmitry Kurtaev
84cec17913 LSTM layer for TensorFlow importer 2017-09-26 12:59:36 +03:00
Dmitry Kurtaev
222149b9c6 Refactored Padding layer 2017-09-22 12:39:00 +03:00
Dmitry Kurtaev
17a85b16fc Remove reorder_dims attribute of Reshape layer 2017-09-21 16:42:03 +03:00
Dmitry Kurtaev
bdd8cc697a Import wrapped Dropout subgraphs from TensorFlow 2017-09-20 13:30:25 +03:00
Vadim Pisarevsky
f7df5dd32c Merge pull request #9305 from dkurt:public_dnn_importer_is_deprecated 2017-09-18 09:35:35 +00:00
Vadim Pisarevsky
e012ccda4a Merge pull request #9517 from dkurt:tf_mobilenet 2017-09-18 09:31:19 +00:00
Dmitry Kurtaev
bd8e6b7e14 Make external cv::dnn::Importer usage is deprecated 2017-09-18 08:52:36 +03:00
Dmitry Kurtaev
d891e9b1d8 Layers for MobileNet from TensorFlow 2017-09-15 20:17:30 +03:00
Dmitry Kurtaev
8646d5fb84 FP16 Caffe models import and export 2017-09-15 18:06:34 +03:00
Vadim Pisarevsky
6bf8fe815d Merge pull request #9384 from dkurt:torch_split 2017-09-15 13:05:05 +00:00
Vadim Pisarevsky
41b23fde9f Merge pull request #9524 from dkurt:dnn_torch_openface 2017-09-15 12:38:12 +00:00
Dmitry Kurtaev
0ce7c33bc8 Torch's Concat and ConcatTable doesn't use Split layer 2017-09-14 09:26:57 +03:00
Dmitry Kurtaev
7dc6b1d7d4 Layers for OpenFace face recognition network 2017-09-14 09:11:31 +03:00
Dmitry Kurtaev
58b890b9f7 Dilated convolution import from TensorFlow 2017-09-13 18:44:14 +03:00
Vadim Pisarevsky
8c7f19850f Merge pull request #9576 from dkurt:feature_dnn_tf_importer_fp16 2017-09-13 13:57:38 +00:00
Vadim Pisarevsky
93c3f20deb Merge pull request #9569 from dkurt:test_dnn_ssd_halide 2017-09-13 13:29:50 +00:00
Dmitry Kurtaev
ce41a15437 Import and convert FP16 weights from TensorFlow 2017-09-12 09:50:55 +03:00
Maksim Shabunin
248e2c7d47 Fixed some issues found by static analysis 2017-09-08 12:22:12 +03:00
Dmitry Kurtaev
cad7c4d51d MobileNet-SSD and VGG-SSD topologies in Halide 2017-09-08 09:55:53 +03:00
Alexander Alekhin
3202bbe17c Merge pull request #9349 from dkurt:tf_deconv 2017-08-24 15:58:38 +00:00
Alexander Alekhin
8e7e24ac80 Merge pull request #9394 from dkurt:fix_halide_wrapper 2017-08-24 15:56:54 +00:00
Alexander Alekhin
25a4559565 Merge pull request #9294 from arrybn:layers_perf 2017-08-24 09:37:49 +00:00
Aleksandr Rybnikov
8b1146deb2 Added function to get timings for layers 2017-08-23 13:40:05 +03:00
Dmitry Kurtaev
54f0616a13 Deconvolution layer from TensorFlow 2017-08-21 21:38:07 +03:00
Dmitry Kurtaev
4e28c00e7b Fix Halide buffer behavior in case of OpenCL device memory allocation 2017-08-17 13:27:54 +03:00
dkurt
339793143c Unit tests for TensorFlow importer 2017-08-03 11:29:48 +03:00
Alexander Alekhin
0bd357e7ec Merge pull request #9296 from dkurt:halide_device_interface 2017-08-02 20:26:30 +00:00
dkurt
b1ef44b1ac Replace halide_opencl_device_interface 2017-08-02 20:38:30 +03:00
Aleksandr Rybnikov
8d6b8b45b6 Added ELU and test for it 2017-08-02 11:13:59 +03:00
Alexander Alekhin
bab4bc0968 Merge pull request #9284 from ipuustin:dnn-opencl-fixes 2017-08-01 13:06:01 +00:00
Ismo Puustinen
c2de5cf735 dnn: force floating point literals to be float. 
In OpenCL code in activations.cl, make the type of floating point
literals to be float. Otherwise the values will be interpreted as
doubles, causing Beignet to have type conversion issues.
 2017-08-01 15:02:24 +03:00
Alexander Alekhin
2959e7aba9 Merge pull request #9188 from arrybn:mobilenet_ssd_sample 2017-08-01 11:12:54 +00:00
Aleksandr Rybnikov
ce1cc352d9 MobileNet SSD sample 2017-08-01 12:30:27 +03:00
Alexander Alekhin
3f102e5d3a dnn: protobuf shutdown 2017-07-26 17:21:46 +03:00
Alexander Alekhin
878a6906cc dnn: fix torch importer memory leaks 2017-07-25 12:20:55 +03:00
Tomoaki Teshima
0f91faddae fix linker error when trying CPU_BASELINE=AVX 2017-07-21 21:13:47 +09:00
Alexander Alekhin
ab58cac236 Merge pull request #9194 from tomoaki0705:fixBuildErrorDnn 2017-07-20 15:27:07 +00:00
Alexander Alekhin
08c94aa5c0 build: reuse int32_t workaround from softfloat.hpp 2017-07-20 14:01:21 +03:00
Tomoaki Teshima
1989bc33a7 fix build error on Visual Studio 2012 2017-07-20 11:00:04 +09:00
Aleksandr Rybnikov
7d1140340e Rewrote googlenet tests 2017-07-18 18:49:14 +03:00
Vadim Pisarevsky
0488d9bdb2 optimize out scaleLayer & concatLayer whenever possible 
fixed problem in concat layer by disabling memory re-use in layers with multiple inputs

trying to fix the tests when Halide is used to run deep nets

another attempt to fix Halide tests

see if the Halide tests will pass with concat layer fusion turned off

trying to fix failures in halide tests; another try

one more experiment to make halide_concat & halide_enet tests pass

continue attempts to fix halide tests

moving on

uncomment parallel concat layer

seemingly fixed failures in Halide tests and re-enabled concat layer fusion; thanks to dkurt for the patch
 2017-07-14 18:30:53 +03:00
Alexander Alekhin
4784c7be5f dnn: cleanup dispatched code, fix SIMD128 types 2017-07-13 19:00:34 +03:00
Alexander Alekhin
c3e6de293f dnn: code cleanup, refactor detection output layer 2017-07-13 19:00:34 +03:00
Alexander Alekhin
544908d06c dnn: some minor fixes in docs, indentation, unused code 2017-07-13 15:33:49 +03:00
Alexander Alekhin
520da7aaaf Merge pull request #9111 from vpisarev:dnn_optim_avx1 2017-07-13 12:27:05 +00:00
dkurt
3203635765 Eltwise layer fixes 2017-07-10 12:58:11 +03:00
Vadim Pisarevsky
ed9564106c reuse AVX2-optimized kernels for AVX1 CPUs (like IvyBridge) 2017-07-06 21:36:59 +03:00
abratchik
8f7181429f add java wrappers to dnn module 2017-07-02 11:46:20 +04:00
Maksim Shabunin
e0393f8557 Fixed some issues found by static analysis (4th round) 2017-06-30 12:26:53 +03:00
Aleksandr Rybnikov
fab4f4b9d5 Disabled logging in caffe parser in release 2017-06-29 17:36:48 +03:00
Vadim Pisarevsky
ac49a17a82 Merge pull request #9022 from dkurt:keep_conv_weights_for_halide 2017-06-29 11:09:17 +00:00
Vadim Pisarevsky
fb1dcdd17d Merge pull request #9029 from alalek:dnn_cleanup_torch 2017-06-29 11:07:35 +00:00
Maksim Shabunin
f1a56cb4b7 Merge pull request #9028 from alalek:dnn_experimental_namespace 2017-06-29 07:37:04 +00:00
Maksim Shabunin
ace0701a46 Merge pull request #9019 from alalek:dnn_trace 2017-06-29 07:33:46 +00:00
Alexander Alekhin
511e50c19c dnn: cleanup torch integration code 2017-06-28 21:49:37 +00:00
Alexander Alekhin
324851882a Merge pull request #9025 from mshabunin:fix-static-3 2017-06-28 20:50:21 +00:00
Alexander Alekhin
da0960321b dnn: added "hidden" experimental namespace 
Main purpose of this namespace is to avoid using of incompatible
binaries that will cause applications crashes.

This additional namespace will not impact "Source code API".
This change allows to maintain ABI checks (with easy filtering out).
 2017-06-28 20:36:57 +00:00
Maksim Shabunin
a769d69a9d Fixed several issues found by static analysis 2017-06-28 18:06:18 +03:00
dkurt
b46f5b1b38 Align convolutional layer weights separately from origin ones 2017-06-28 17:05:56 +03:00
Alexander Alekhin
ed10383359 dnn: added trace macros 2017-06-28 14:57:26 +03:00
Vadim Pisarevsky
c5faa9aefa Merge pull request #9013 from arrybn:ssd_last_layers_optim 2017-06-28 10:38:55 +00:00
Vadim Pisarevsky
bbb14d3746 Merge pull request #9003 from dkurt:halide_bug_fixes 2017-06-28 08:48:27 +00:00
Aleksandr Rybnikov
ec321e651f Removed usage of std::map in DetectionOutput layer 2017-06-28 11:31:38 +03:00
Vadim Pisarevsky
2ae849091c Merge pull request #9009 from alalek:fix_dnn_initialization 2017-06-28 08:26:29 +00:00
Vadim Pisarevsky
8b3d6603d5 another round of dnn optimization (#9011) 
* another round of dnn optimization:
* increased malloc alignment across OpenCV from 16 to 64 bytes to make it AVX2 and even AVX-512 friendly
* improved SIMD optimization of pooling layer, optimized average pooling
* cleaned up convolution layer implementation
* made activation layer "attacheable" to all other layers, including fully connected and addition layer.
* fixed bug in the fusion algorithm: "LayerData::consumers" should not be cleared, because it desctibes the topology.
* greatly optimized permutation layer, which improved SSD performance
* parallelized element-wise binary/ternary/... ops (sum, prod, max)

* also, added missing copyrights to many of the layer implementation files

* temporarily disabled (again) the check for intermediate blobs consistency; fixed warnings from various builders
 2017-06-28 11:15:22 +03:00
Alexander Alekhin
00dd433368 dnn: fix LayerFactory initialization 2017-06-27 23:19:53 +03:00
Alexander Alekhin
f8a75c4361 dispatch: added CV_TRY_${OPT} macro, fix dnn build 
- 1: OPT is available directly or via dispatcher
- 0: optimization is not compiled at all
 2017-06-27 17:05:15 +03:00
dkurt
121789f78e Fixed some bugs from Halide tests 2017-06-27 14:52:46 +03:00
Alexander Alekhin
16d1bbf2ea dnn: fix build 
- winpack
- opencv_world
 2017-06-27 09:07:01 +03:00
Alexander Alekhin
986d27e49c dnn: fix failed Torch tests 
"Torch invalid argument 2: position must be smaller than LLONG_MAX"

These conditions are always true for "long position" argument.
 2017-06-26 22:02:22 +03:00
Alexander Alekhin
93091ba203 dnn: AVX2 fix invalid unaligned read 2017-06-26 19:48:42 +03:00
Alexander Alekhin
93729784bb dnn: move module from opencv_contrib 
e6f63c7a38/modules/dnn
 2017-06-26 13:41:51 +03:00