Commit Graph

55 Commits

Author SHA1 Message Date
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
Lubov Batanina
cfc781949d Merge pull request #15811 from l-bat:eltwise_div
Supported ONNX Squeeze, ReduceL2 and Eltwise::DIV

* Support eltwise div

* Fix test

* OpenCL support added

* refactoring

* fix code style

* Only squeeze with axes supported
2019-11-09 14:11:09 +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
feff8bf972 Merge pull request #15626 from alalek:dnn_openvino_2019r3 2019-10-04 19:45:37 +00:00
Dmitry Kurtaev
e35fd463e7 Enable ENet with Inference Engine backend on CPU 2019-10-04 18:10:11 +03:00
Alexander Alekhin
fd11e3a81d dnn: update IE tests 2019-10-04 17:49:10 +03:00
Maksim Shabunin
4dadf17bd9 Merge pull request #15168 from dkurt:dnn_onnx_15120 2019-07-31 15:03:23 +00:00
Dmitry Kurtaev
f9f160404a Add support for slice from ONNX with multiple outputs 2019-07-28 21:20:25 +03:00
Dmitry Kurtaev
ebaefbb745 Remove VGG16 from ONNX test because there is VGG16_bn 2019-07-27 23:04:25 +03:00
Lubov Batanina
781f4d439e Merge pull request #15032 from l-bat:reduce_mean
* Added support for the ONNX "ReduceMean" Layer. (as this is the same as the GlobalAveragePool)

* Add ReduceMean test

* Fix ONNX importer

* Fix ReduceMean

* Add assert

* Split test

* Fix split test
2019-07-19 19:18:34 +03:00
Alexander Alekhin
5ccb2a4cbd dnn(test): fix required data 2019-07-16 07:53:50 +00:00
Lubov Batanina
34f6b05467 Merge pull request #14996 from l-bat:ocv_deconv3d
* Support Deconvolution3D on IE backend

* Add test tag

* Fix tests
2019-07-12 15:51:44 +03:00
Lubov Batanina
8bcd7e122a Merge pull request #14842 from l-bat:ocv_conv3d
* Support Conv3D on OCV backend

* Add header

* Add perf tests

* Support pool3d

* Enable Resnet34_kinetics on OCV backend

* Add test

* Fix conv

* Optimize Conv2D
2019-07-11 20:13:52 +03:00
Diego
57fae4a6a1 Merge pull request #14858 from dvd42:instancenorm_onnx
Instancenorm onnx (#14858)

* Onnx unsupported operation handling

* instance norm implementation

* Revert "Onnx unsupported operation handling"

* instance norm layer test

* onnx instancenorm layer
2019-07-04 21:15:04 +03:00
Diego
6dfe2ddc21 Merge pull request #14959 from dvd42:onnx_clip
* onnx clip operation
2019-07-04 08:56:00 +03:00
Dmitry Kurtaev
75f4c1abf2 Enable some tests for Inference Engine backend 2019-06-28 15:52:31 +03:00
Alexander Alekhin
894f208de3 dnn(test): replace SkipTestException with tags 2019-06-23 13:12:23 +00:00
Alexander Alekhin
f8c96cb18a Merge pull request #14847 from alalek:dnn_fix_test_data_searching 2019-06-23 12:42:27 +00:00
Lubov Batanina
16294437d5 Merge pull request #14833 from l-bat:ocv_eltwise3d
* Support Eltwise3d

* Refactoring

* Fix test
2019-06-22 10:13:28 +03:00
Alexander Alekhin
13a782c039 test: fix usage of findDataFile()
misused 'optional' mode
2019-06-20 18:20:14 +03:00
Dmitry Kurtaev
eba696a41e Merge pull request #14792 from dkurt:dnn_ie_min_version_r5
* Remove Inference Engine 2018R3 and 2018R4

* Fix 2018R5
2019-06-14 18:17:02 +03:00
Lubov Batanina
5e80191d27 Merge pull request #14697 from l-bat:Slice_ONNX
* Support Slice layer in ONNX importer

* Add IE support

* Fix ONNX importer

* Fix Slice
2019-06-08 16:52:40 +03:00
Lubov Batanina
f94253b82b Merge pull request #14627 from l-bat:demo_kinetics
* Support 3D ResNet-34-kinetics

* Update sample

* Remove preprocess

* Change test

* Fix sample
2019-05-30 17:36:00 +03:00
Alexander Alekhin
38a3c1ce6b dnn(test): update test tags for Debug build 2019-05-27 20:12:30 +00:00
Dmitry Kurtaev
26e426adb1 StridedSlice from TensorFlow 2019-05-22 12:45:52 +03:00
dianlujitao
f0f50b757d Fix LogSoftmax for ONNX
Fix wrong indentation as well while at it
2019-05-20 22:55:31 +08:00
Liubov Batanina
dfa753c6b4 Support OCV backend 2019-05-14 16:44:57 +03:00
Liubov Batanina
dadb1473c1 Add BatchNorm3d layer 2019-05-14 12:44:48 +03:00
Alexander Alekhin
163d5e4d39 Merge pull request #14368 from dkurt:dnn_ie_tests 2019-04-30 19:35:00 +00:00
Lubov Batanina
77fa59c3da Merge pull request #14301 from l-bat:conv3d
Support Convolution3D layer on IE backend (#14301)

* Add Convolution3D layer

* Disable CXX11

* Fixed tests

* Add Pooling3D layer

* Merge Conv2d with Conv3d and Pool2d with Pool3d layers

* Split pads

* Add Deconvolution layer

* Refactoring

* Deduplication

* Refactoring

* Add utils for Convolution and Pooling layers
2019-04-30 17:08:17 +03:00
Dmitry Kurtaev
4f6be11c0e Check if Inference Engine networks are fully supported by backend 2019-04-25 11:27:17 +03:00
Liubov Batanina
45ced8e022 Fix ONNX deconvolution 2019-04-24 14:37:52 +03:00
Alexander Alekhin
64629cb94e Merge pull request #12783 from alalek:test_tag 2019-04-12 15:35:41 +00:00
Dmitry Kurtaev
a2bbfa1db5 Enable some tests for Inference Engine 2019R1 2019-04-12 15:21:42 +03:00
Alexander Alekhin
e0841f3d6e dnn(test-tags): add time / memory tags 2019-04-08 19:18:25 +00:00
Alexander Alekhin
8483801eab dnn: use OpenVINO 2019R1 defines 2019-04-03 15:39:47 +03:00
Lubov Batanina
7d3d6bc4e2 Merge pull request #13932 from l-bat:MyriadX_master_dldt
* Fix precision in tests for MyriadX

* Fix ONNX tests

* Add output range in ONNX tests

* Skip tests on Myriad OpenVINO 2018R5

* Add detect MyriadX

* Add detect MyriadX on OpenVINO R5

* Skip tests on Myriad next version of OpenVINO

* dnn(ie): VPU type from environment variable

* dnn(test): validate VPU type

* dnn(test): update DLIE test skip conditions
2019-03-29 16:42:58 +03:00
Kohei Yoshida
212420516f Add a test case for handling output_shape property for deconvolution layer. 2019-03-26 10:46:17 -04:00
Alexander Alekhin
865c29a754 Merge pull request #13892 from dkurt:onnx_upsample_unsqueeze 2019-02-26 10:17:07 +00:00
Dmitry Kurtaev
20400aa9f7 Import Upsample and Unsqueeze from ONNX 2019-02-21 20:17:28 +03:00
Dmitry Kurtaev
bfd663c281 Add a test for grouped deconvolution from ONNX 2019-02-21 08:54:35 +03:00
Dmitry Kurtaev
c918ac298c Fix IE tests 2019-01-31 14:14:38 +03:00
Dmitry Kurtaev
f0ddf302b2 Move Inference Engine to new API 2019-01-17 14:28:48 +03:00
Dmitry Kurtaev
59ce1d80a5 Fix dnn tests for Inference Engine R5 2018-12-21 12:33:30 +03:00
Dmitry Kurtaev
e71758cfdf Operate with shapes in ONNX models 2018-12-12 18:34:22 +03:00
Christopher Gundler
b58a8729c2 Merge pull request #13131 from Christopher22:add_transposedConv_onnx
* Add support for ConvTranspose when parsing ONNX.

* Add support for ConvTranspose when parsing ONNX.

* Add test for Deconvolution
2018-11-16 22:50:40 +03:00
Alexander Alekhin
96c71dd3d2 dnn: reduce set of ignored warnings 2018-11-15 13:15:59 +03:00
Dmitry Kurtaev
a6f9170f10 Add ONNX's padding import 2018-10-31 18:24:05 +03:00