Commit Graph

27494 Commits

Author SHA1 Message Date
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
8ec6544624 Merge pull request #15747 from TH3CHARLie:imshow-fix 2019-10-20 13:08:40 +00:00
Alexander Alekhin
a8d14e88fe Merge pull request #15743 from collinbrake:feature_grammar_fixes_2 2019-10-20 13:08:28 +00:00
Alexander Alekhin
6576e8b927 Merge pull request #14518 from SSteve:intersectConvexConvex-example 2019-10-20 13:06:27 +00:00
Steve Nicholson
acb3b3bd4d Add documentation and example program for intersectConvexConvex 2019-10-19 22:08:07 -07:00
TH3CHARLie
da0fec7308 fix incorrect imshow behavior 2019-10-19 20:34:18 +08:00
Dmitry Kurtaev
af61a15839 Fix Darknet eltwise 2019-10-19 12:54:15 +03:00
collin
3ada597449 grammar corrections for python gui docs 2019-10-18 17:42:56 -04:00
Alexander Alekhin
938d8dce06 Merge pull request #15685 from pmur:cnz64f-simd 2019-10-18 20:19:40 +00:00
Alexander Alekhin
6e85e852d4 Merge pull request #15740 from xerus:fix_typo 2019-10-18 18:41:35 +00:00
Alexander Alekhin
70a5553499 Merge pull request #15741 from mipsopen-fwu:issue_15730 2019-10-18 18:40:25 +00:00
Fei Wu
90af2835a2 Fix issue 15730. 2019-10-19 00:36:18 +08:00
Pavel Grunt
83e2e124a3 OpenCVFindMKL: Fix a typo 2019-10-18 18:33:06 +02:00
Dmitry Matveev
2477103707 Merge pull request #15216 from dmatveev:dm/ng-0010-g-api-streaming-api
* G-API-NG/Streaming: Introduced a Streaming API

Now a GComputation can be compiled in a special "streaming" way
and then "played" on a video stream.

Currently only VideoCapture is supported as an input source.

* G-API-NG/Streaming: added threading & real streaming

* G-API-NG/Streaming: Added tests & docs on Copy kernel

- Added very simple pipeline tests, not all data types are covered yet
  (in fact, only GMat is tested now);
- Started testing non-OCV backends in the streaming mode;
- Added required fixes to Fluid backend, likely it works OK now;
- Added required fixes to OCL backend, and now it is likely broken
- Also added a UMat-based (OCL) version of Copy kernel

* G-API-NG/Streaming: Added own concurrent queue class

- Used only if TBB is not available

* G-API-NG/Streaming: Fixing various issues

- Added missing header to CMakeLists.txt
- Fixed various CI issues and warnings

* G-API-NG/Streaming: Fixed a compile-time GScalar queue deadlock

- GStreamingExecutor blindly created island's input queues for
  compile-time (value-initialized) GScalars which didn't have any
  producers, making island actor threads wait there forever

* G-API-NG/Streaming: Dropped own version of Copy kernel

One was added into master already

* G-API-NG/Streaming: Addressed GArray<T> review comments

- Added tests on mov()
- Removed unnecessary changes in garray.hpp

* G-API-NG/Streaming: Added Doxygen comments to new public APIs

Also fixed some other comments in the code

* G-API-NG/Streaming: Removed debug info, added some comments & renamed vars

* G-API-NG/Streaming: Fixed own-vs-cv abstraction leak

- Now every island is triggered with own:: (instead of cv::)
  data objects as inputs;
- Changes in Fluid backend required to support cv::Mat/Scalar were
  reverted;

* G-API-NG/Streaming: use holds_alternative<> instead of index/index_of test

- Also fixed regression test comments
- Also added metadata check comments for GStreamingCompiled

* G-API-NG/Streaming: Made start()/stop() more robust

- Fixed various possible deadlocks
- Unified the shutdown code
- Added more tests covering different corner cases on start/stop

* G-API-NG/Streaming: Finally fixed Windows crashes

In fact the problem hasn't been Windows-only.
Island thread popped data from queues without preserving the Cmd
objects and without taking the ownership over data acquired so when
islands started to process the data, this data may be already freed.

Linux version worked only by occasion.

* G-API-NG/Streaming: Fixed (I hope so) Windows warnings

* G-API-NG/Streaming: fixed typos in internal comments

- Also added some more explanation on Streaming/OpenCL status

* G-API-NG/Streaming: Added more unit tests on streaming

- Various start()/stop()/setSource() call flow combinations

* G-API-NG/Streaming: Added tests on own concurrent bounded queue

* G-API-NG/Streaming: Added more tests on various data types, + more

- Vector/Scalar passed as input;
- Vector/Scalar passed in-between islands;
- Some more assertions;
- Also fixed a deadlock problem when inputs are mixed (1 constant, 1 stream)

* G-API-NG/Streaming: Added tests on output data types handling

- Vector
- Scalar

* G-API-NG/Streaming: Fixed test issues with IE + Windows warnings

* G-API-NG/Streaming: Decoupled G-API from videoio

- Now the core G-API doesn't use a cv::VideoCapture directly,
  it comes in via an abstract interface;
- Polished a little bit the setSource()/start()/stop() semantics,
  now setSource() is mandatory before ANY call to start().

* G-API-NG/Streaming: Fix STANDALONE build (errors brought by render)
2019-10-18 19:29:58 +03:00
Dmitry Kurtaev
adbd613660 Enable Eltwise layer with different numbers of inputs channels 2019-10-18 18:51:52 +03:00
Alexander Alekhin
849d8d31fe Merge pull request #15737 from alalek:issue_15705 2019-10-18 14:52:26 +00:00
Alexander Alekhin
24ebca5c59 core(simd): v_reverse() for MSA backend 2019-10-18 16:43:03 +03:00
Alexander Alekhin
ead7d6d80f Merge pull request #15716 from alalek:javadoc_fix 2019-10-17 22:35:14 +00:00
Alexander Alekhin
34df28db2b Merge pull request #15180 from terfendail:wintr_stereobm 2019-10-17 20:18:30 +00:00
atalaman
2ff12c4981 Merge pull request #15699 from TolyaTalamanov:at/graph-ocv-render-backend-skeleton
G-API: Implement OpenCV render backend

* Implement render opencv backend

* Fix comment to review

* Add comment

* Add wrappers for kernels

* Fix comments to review

* Fix comment to review
2019-10-17 21:04:03 +03:00
Alexander Alekhin
a2b3cd9a2c Merge pull request #15709 from alalek:js_simd_reverse 2019-10-17 13:14:50 +00:00
Alexander Alekhin
d31da08d43 Merge pull request #15708 from alalek:js_simd_support_1.38.48 2019-10-17 13:14:34 +00:00
Alexander Alekhin
17e9fde75a Merge pull request #15718 from alalek:pylint_warnings 2019-10-17 10:46:03 +00:00
Alexander Smorkalov
692e1eccb6 Merge pull request #15720 from alalek:cmake_fix_uwp 2019-10-17 10:35:27 +00:00
Alexander Smorkalov
009f5f74ef Merge pull request #15722 from jasjuang:3.4 2019-10-17 10:19:47 +00:00
jasjuang
4c7db02925 document CC_STAT_MAX in ConnectedComponentsTypes 2019-10-16 17:22:25 -07:00
Alexander Alekhin
c4e2e17b0c cmake: fix UWP scripts path 2019-10-16 21:42:31 +00:00
Alexander Alekhin
9255df44d0 Merge pull request #15715 from adamrankin:patch-1 2019-10-16 18:52:10 +00:00
Alexander Alekhin
0e40c8a031 fix pylint warnings
pylint 1.8.3
2019-10-16 18:49:33 +03:00
Alexander Alekhin
86e7d82418 javadoc: fix generation with OpenJDK 11 2019-10-16 18:14:07 +03:00
Adam Rankin
3b070517ad
COMP: Enabling build with recent VTK version
VTK_MAJOR_VERSION not found unless header is included
2019-10-16 10:04:41 -04:00
Alexander Alekhin
ad5d14ec0e Merge pull request #15701 from alalek:issue_15691 2019-10-16 11:13:07 +00:00
Alexander Alekhin
bce653117f Merge pull request #15700 from alalek:issue_12943 2019-10-16 11:12:49 +00:00
Alexander Alekhin
ad172726c0 js(simd): v_reverse implementation 2019-10-15 18:46:08 +03:00
Alexander Alekhin
cc9b199ecb Merge pull request #15704 from alalek:gapi_avoid_dynamic_initializers_in_optimized_code 2019-10-15 15:22:09 +00:00
Alexander Alekhin
b1a8de0901 js(simd): support Emscripten 1.38.48-upstream 2019-10-15 15:39:22 +03:00
Alexander Alekhin
823884b064 core(alloc): force initialization of memalign flag
- before main() launch
2019-10-15 13:07:11 +03:00
Alexander Alekhin
a84969bdcd gapi: avoid dynamic initialization in dispatched files 2019-10-14 23:07:57 +00:00
Alexander Alekhin
6a7d1c15d3 core(ipp): skip huge input in flip()
- IPP/SSE4.2 works well
2019-10-14 18:26:19 +03:00
Alexander Alekhin
823e767eed Merge pull request #15684 from OrestChura:id_helper_class_semicolon_issue 2019-10-14 09:46:41 +00:00
Alexander Alekhin
e42560bed5 Merge pull request #15659 from malfet:use-atomic-in-getExpTab32f 2019-10-12 20:27:58 +00:00
Alexander Alekhin
d6630ab35b Merge pull request #15655 from malfet:use-atomic-in-parallel-for 2019-10-12 20:26:15 +00:00
Alexander Smorkalov
d154fa4b4c Merge pull request #15688 from JamesNewton:3.4 2019-10-12 18:05:55 +00:00
JamesNewton
47fc889df0
Update js_image_arithmetics.markdown 2019-10-11 10:07:22 -07:00
Chip Kerchner
027769bf5d Merge pull request #15662 from ChipKerchner:addVReverseIntrinsic
* New v_reverse HAL intrinsic for reversing the ordering of a vector

* Fix conflict.

* Try to resolve conflict again.

* Try one more time.

* Add _MM_SHUFFLE. Remove non-vectorize code in SSE2. Fix copy and paste issue with NEON.

* Change v_uint16x8 SSE2 version to use shuffles
2019-10-11 18:34:17 +03:00
Everton Constantino
9ca9249992 Merge pull request #15527 from everton1984:faster_acc
* Adding support for vectorized masking for uchar/ushort.

* Fixing bug where mask was zeroing the dst. Improved the way to calculate
the mask and tweaked for further performance improvements.

* Fixing mask comparison test.

* Restricting to one channel.

* Adding support for 3 channels, switch old approach to start using HAL's
v_select.
2019-10-11 18:32:59 +03:00
Paul E. Murphy
ec91a3d59d core: vectorize countNonZero64f
Improves performance a bit. 2.2x on P9 and 2 - 3x on coffee lake
x86-64.
2019-10-11 09:02:46 -05:00
Alexander Alekhin
2f30c3fd4f Merge pull request #15681 from mshabunin:fix-gapi-ie-test 2019-10-11 13:12:45 +00:00
OrestChura
2f9351d995 Fix warning issue:
- unnecessary extra semicolon after member function definition removed
2019-10-10 18:48:27 +03:00
Maksim Shabunin
230e44b01d G-API: removed deprecated IE call from test 2019-10-10 12:58:59 +03:00