Commit Graph

54 Commits

Author SHA1 Message Date
Alexander Alekhin
fa25faa2d2 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2020-08-06 14:15:52 +00:00
Dmitry Kurtaev
cf8f65d806 Do not use size_t for nGraph layers 2020-08-02 20:50:44 +03:00
Alexander Alekhin
bfcc136dc7 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2020-04-21 21:32:51 +00:00
Dmitry Kurtaev
908bf935f7 Flexible inputs for OpenVINO IR models 2020-04-18 20:00:22 +03:00
Alexander Alekhin
124bf8339f dnn(IE): use HAVE_DNN_IE_NN_BUILDER_2019 for NN Builder API code
- CMake option: OPENCV_DNN_IE_NN_BUILDER_2019
2020-03-03 08:07:54 +00:00
Alexander Alekhin
29d214474f dnn(IE): use HAVE_DNN_IE_NN_BUILDER_2019 for NN Builder API code
- CMake option: OPENCV_DNN_IE_NN_BUILDER_2019
2020-03-03 07:45:09 +00:00
Alexander Alekhin
45d073f889 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2020-02-26 20:09:03 +03:00
Alexander Alekhin
f48c84eaee Merge pull request #16656 from alalek:issue_16655 2020-02-26 12:47:46 +00:00
Alexander Alekhin
d54d01ca46 core(MatExpr): fix .type() bug 2020-02-23 17:05:05 +00:00
Alexander Alekhin
01048e5603
Merge pull request #16616 from alalek:dnn_fix_input_shape
* dnn: fix processing of input shapes

- importer: avoid using of .setInput() => .setInputShape()
- setInput: shape limitation check (partial)

* dnn(test): test .setInput() in readNet()
2020-02-21 22:39:54 +03:00
Alexander Alekhin
aa2777ed61 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2020-02-10 19:40:29 +03:00
Alexander Alekhin
8ecfb59930 dnn(test): skip failed ngraph tests 2020-02-07 22:43:40 +00:00
Alexander Alekhin
4c86fc13cb Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2019-12-19 15:09:05 +03:00
antalzsiroscandid
aa80f754f4 dnn: reading IR models from buffer 2019-12-18 15:31:08 +01:00
Alexander Alekhin
1633c29f29 Merge pull request #16037 from alalek:dnn_test_fix_skip_vulkan 2019-12-04 15:49:47 +00:00
Alexander Alekhin
0dc0bc80ae dnn(test): fix Vulkan skip test tag 2019-12-02 18:22:10 +03:00
Alexander Alekhin
4b0132ed7a Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2019-12-02 16:26:52 +03:00
Lubov Batanina
7523c777c5 Merge pull request #15537 from l-bat:ngraph
* Support nGraph

* Fix resize
2019-12-02 16:16:06 +03:00
Alexander Alekhin
b6a58818bb Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2019-11-11 20:25:42 +00:00
Dimitri Gerin
7c4158d8c2 Fix dnn::getLayerInputs 2019-11-07 08:13:33 +03:00
Yashas Samaga B L
613c12e590 Merge pull request #14827 from YashasSamaga:cuda4dnn-csl-low
CUDA backend for the DNN module

* stub cuda4dnn design

* minor fixes for tests and doxygen

* add csl public api directory to module headers

* add low-level CSL components

* add high-level CSL components

* integrate csl::Tensor into backbone code

* switch to CPU iff unsupported; otherwise, fail on error

* add fully connected layer

* add softmax layer

* add activation layers

* support arbitary rank TensorDescriptor

* pass input wrappers to `initCUDA()`

* add 1d/2d/3d-convolution

* add pooling layer

* reorganize and refactor code

* fixes for gcc, clang and doxygen; remove cxx14/17 code

* add blank_layer

* add LRN layer

* add rounding modes for pooling layer

* split tensor.hpp into tensor.hpp and tensor_ops.hpp

* add concat layer

* add scale layer

* add batch normalization layer

* split math.cu into activations.cu and math.hpp

* add eltwise layer

* add flatten layer

* add tensor transform api

* add asymmetric padding support for convolution layer

* add reshape layer

* fix rebase issues

* add permute layer

* add padding support for concat layer

* refactor and reorganize code

* add normalize layer

* optimize bias addition in scale layer

* add prior box layer

* fix and optimize normalize layer

* add asymmetric padding support for pooling layer

* add event API

* improve pooling performance for some padding scenarios

* avoid over-allocation of compute resources to kernels

* improve prior box performance

* enable layer fusion

* add const layer

* add resize layer

* add slice layer

* add padding layer

* add deconvolution layer

* fix channelwise  ReLU initialization

* add vector traits

* add vectorized versions of relu, clipped_relu, power

* add vectorized concat kernels

* improve concat_with_offsets performance

* vectorize scale and bias kernels

* add support for multi-billion element tensors

* vectorize prior box kernels

* fix address alignment check

* improve bias addition performance of conv/deconv/fc layers

* restructure code for supporting multiple targets

* add DNN_TARGET_CUDA_FP64

* add DNN_TARGET_FP16

* improve vectorization

* add region layer

* improve tensor API, add dynamic ranks

1. use ManagedPtr instead of a Tensor in backend wrapper
2. add new methods to tensor classes
  - size_range: computes the combined size of for a given axis range
  - tensor span/view can be constructed from a raw pointer and shape
3. the tensor classes can change their rank at runtime (previously rank was fixed at compile-time)
4. remove device code from tensor classes (as they are unused)
5. enforce strict conditions on tensor class APIs to improve debugging ability

* fix parametric relu activation

* add squeeze/unsqueeze tensor API

* add reorg layer

* optimize permute and enable 2d permute

* enable 1d and 2d slice

* add split layer

* add shuffle channel layer

* allow tensors of different ranks in reshape primitive

* patch SliceOp to allow Crop Layer

* allow extra shape inputs in reshape layer

* use `std::move_backward` instead of `std::move` for insert in resizable_static_array

* improve workspace management

* add spatial LRN

* add nms (cpu) to region layer

* add max pooling with argmax ( and a fix to limits.hpp)

* add max unpooling layer

* rename DNN_TARGET_CUDA_FP32 to DNN_TARGET_CUDA

* update supportBackend to be more rigorous

* remove stray include from preventing non-cuda build

* include op_cuda.hpp outside condition #if

* refactoring, fixes and many optimizations

* drop DNN_TARGET_CUDA_FP64

* fix gcc errors

* increase max. tensor rank limit to six

* add Interp layer

* drop custom layers; use BackendNode

* vectorize activation kernels

* fixes for gcc

* remove wrong assertion

* fix broken assertion in unpooling primitive

* fix build errors in non-CUDA build

* completely remove workspace from public API

* fix permute layer

* enable accuracy and perf. tests for DNN_TARGET_CUDA

* add asynchronous forward

* vectorize eltwise ops

* vectorize fill kernel

* fixes for gcc

* remove CSL headers from public API

* remove csl header source group from cmake

* update min. cudnn version in cmake

* add numerically stable FP32 log1pexp

* refactor code

* add FP16 specialization to cudnn based tensor addition

* vectorize scale1 and bias1 + minor refactoring

* fix doxygen build

* fix invalid alignment assertion

* clear backend wrappers before allocateLayers

* ignore memory lock failures

* do not allocate internal blobs

* integrate NVTX

* add numerically stable half precision log1pexp

* fix indentation, following coding style,  improve docs

* remove accidental modification of IE code

* Revert "add asynchronous forward"

This reverts commit 1154b9da9da07e9b52f8a81bdcea48cf31c56f70.

* [cmake] throw error for unsupported CC versions

* fix rebase issues

* add more docs, refactor code, fix bugs

* minor refactoring and fixes

* resolve warnings/errors from clang

* remove haveCUDA() checks from supportBackend()

* remove NVTX integration

* changes based on review comments

* avoid exception when no CUDA device is present

* add color code for CUDA in Net::dump
2019-10-21 14:28:00 +03:00
Alexander Alekhin
3fb6617d62 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2019-10-02 17:49:19 +03:00
Alexander Alekhin
440a937d24 dnn: increase async test timeout 2019-10-01 13:31:57 +03:00
Alexander Alekhin
2ad0487cec Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2019-08-13 18:32:29 +00:00
Lubov Batanina
0e1ef8f8e1 Merge pull request #15184 from l-bat:IE_R2
Support new IE API (#15184)

* Add support OpenVINO R2 for layers

* Add Core API

* Fix tests

* Fix expectNoFallbacksFromIE for ONNX nets

* Remove deprecated API

* Remove td

* Remove TargetDevice

* Fix Async

* Add test

* Fix detectMyriadX

* Fix test

* Fix warning
2019-08-06 22:20:26 +03:00
Alexander Alekhin
199ddff13b Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2019-07-18 20:25:25 +00:00
Lubov Batanina
12fdaf895e Merge pull request #15057 from l-bat:fix_vizualizer
* Fix dumpToFile

* Add test

* Fix test
2019-07-18 18:41:08 +03:00
Alexander Alekhin
b95e93c20a Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2019-06-26 20:19:04 +00:00
Alexander Alekhin
894f208de3 dnn(test): replace SkipTestException with tags 2019-06-23 13:12:23 +00:00
Alexander Alekhin
13a782c039 test: fix usage of findDataFile()
misused 'optional' mode
2019-06-20 18:20:14 +03:00
Alexander Alekhin
11b020b9f9 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2019-06-10 19:05:28 +00:00
Alexander Alekhin
132253c9f3 dnn: use AsyncArray 2019-05-18 19:32:23 +00:00
Alexander Alekhin
b2abd8ca41 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2019-05-07 16:04:54 +00:00
Dmitry Kurtaev
adc1ef9308 Fix uint8 input data for Async mode of dnn 2019-05-05 12:49:38 +03:00
Alexander Alekhin
d0032b0717 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2019-04-22 18:17:28 +00:00
Dmitry Kurtaev
a5c92c2029 Merge pull request #13694 from dkurt:dnn_ie_async
Asynchronous API from Intel's Inference Engine (#13694)

* Add forwardAsync for asynchronous mode from Intel's Inference Engine

* Python test for forwardAsync

* Replace Future_Mat to AsyncMat

* Shadow AsyncMat

* Isolate InferRequest callback

* Manage exceptions in Async API of IE
2019-04-19 21:01:19 +03:00
Alexander Alekhin
665408e57f Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2019-02-01 13:17:32 +03:00
Dmitry Kurtaev
3c3c5ef2b6 Fix a dnn bug with retrieving all the output blobs 2019-01-28 18:48:56 +03:00
Alexander Alekhin
e82e672a93 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2018-12-06 07:06:58 +00:00
Maksim Shabunin
fe459c82e5 Merge pull request #13332 from mshabunin:dnn-backends
DNN backends registry (#13332)

* Added dnn backends registry

* dnn: process DLIE/FPGA target
2018-12-05 18:11:45 +03:00
Alexander Alekhin
7fa7fa0226 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2018-11-21 08:33:39 +00:00
Dmitry Kurtaev
0d117312c9 DNN_TARGET_FPGA using Intel's Inference Engine 2018-11-19 11:41:43 +03:00
Alexander Alekhin
22dbcf98c5 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2018-11-17 14:17:35 +00:00
Alexander Alekhin
96c71dd3d2 dnn: reduce set of ignored warnings 2018-11-15 13:15:59 +03:00
WuZhiwen
6e3ea8b49d Merge pull request #12703 from wzw-intel:vkcom
* dnn: Add a Vulkan based backend

This commit adds a new backend "DNN_BACKEND_VKCOM" and a
new target "DNN_TARGET_VULKAN". VKCOM means vulkan based
computation library.

This backend uses Vulkan API and SPIR-V shaders to do
the inference computation for layers. The layer types
that implemented in DNN_BACKEND_VKCOM include:
Conv, Concat, ReLU, LRN, PriorBox, Softmax, MaxPooling,
AvePooling, Permute

This is just a beginning work for Vulkan in OpenCV DNN,
more layer types will be supported and performance
tuning is on the way.

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

* dnn/vulkan: Add FindVulkan.cmake to detect Vulkan SDK

In order to build dnn with Vulkan support, need installing
Vulkan SDK and setting environment variable "VULKAN_SDK" and
add "-DWITH_VULKAN=ON" to cmake command.

You can download Vulkan SDK from:
https://vulkan.lunarg.com/sdk/home#linux

For how to install, see
https://vulkan.lunarg.com/doc/sdk/latest/linux/getting_started.html
https://vulkan.lunarg.com/doc/sdk/latest/windows/getting_started.html
https://vulkan.lunarg.com/doc/sdk/latest/mac/getting_started.html
respectively for linux, windows and mac.

To run the vulkan backend, also need installing mesa driver.
On Ubuntu, use this command 'sudo apt-get install mesa-vulkan-drivers'

To test, use command '$BUILD_DIR/bin/opencv_test_dnn --gtest_filter=*VkCom*'

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

* dnn/Vulkan: dynamically load Vulkan runtime

No compile-time dependency on Vulkan library.
If Vulkan runtime is unavailable, fallback to CPU path.

Use environment "OPENCL_VULKAN_RUNTIME" to specify path to your
own vulkan runtime library.

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

* dnn/Vulkan: Add a python script to compile GLSL shaders to SPIR-V shaders

The SPIR-V shaders are in format of text-based 32-bit hexadecimal
numbers, and inserted into .cpp files as unsigned int32 array.

* dnn/Vulkan: Put Vulkan headers into 3rdparty directory and some other fixes

Vulkan header files are copied from
https://github.com/KhronosGroup/Vulkan-Docs/tree/master/include/vulkan
to 3rdparty/include

Fix the Copyright declaration issue.

Refine OpenCVDetectVulkan.cmake

* dnn/Vulkan: Add vulkan backend tests into existing ones.

Also fixed some test failures.

- Don't use bool variable as uniform for shader
- Fix dispathed group number beyond max issue
- Bypass "group > 1" convolution. This should be support in future.

* dnn/Vulkan: Fix multiple initialization in one thread.
2018-10-29 17:51:26 +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
070393dfda uint8 inputs for deep learning networks 2018-07-19 14:37:33 +03:00
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
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
f2440ceae6 Update tutorials. A new cv::dnn::readNet function 2018-03-04 20:30:22 +03:00