YashasSamaga
fbb3f64a1a
fix expm1 and log1p for __half/__half2
5 years ago
Alexander Alekhin
0dc0bc80ae
dnn(test): fix Vulkan skip test tag
5 years ago
Lubov Batanina
7523c777c5
Merge pull request #15537 from l-bat:ngraph
...
* Support nGraph
* Fix resize
5 years ago
Manjunath Bhat
78c5e41c23
Merge pull request #15808 from thebhatman:Mish_swish
...
* Added Swish and Mish activations
* Fixed whitespace errors
* Kernel implementation done
* Added function for launching kernel
* Changed type of 1.0
* Attempt to add test for Swish and Mish
* Resolving type mismatch for log
* exp from device
* Use log1pexp instead of adding 1
* Added openCL kernels
5 years ago
thebhatman
8a18d132fc
Port Swish and Mish layers
5 years ago
Brian Wignall
9276f1910b
Fix some typos
5 years ago
Dmitry Kurtaev
6e14cc2189
Resolve https://github.com/opencv/opencv/issues/15863
5 years ago
Alexander Alekhin
86042af108
dnn: fix registration of custom OpenCVLayer
...
- do not require extensions library
5 years ago
Alexander Alekhin
09d54c9f52
dnn: update InferenceEngine extension handling
5 years ago
Alexander Alekhin
7ec91aefc1
python: force using of ArgInfo
5 years ago
Liubov Batanina
ac4fd4f4ae
Fix ReduceL2
5 years ago
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
5 years ago
Dimitri Gerin
7c4158d8c2
Fix dnn::getLayerInputs
5 years ago
Dmitry Kurtaev
dfe0368835
Fix custom IE layers in case of no MKLDNN plugin
5 years ago
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
5 years ago
Dmitry Kurtaev
af61a15839
Fix Darknet eltwise
5 years ago
Dmitry Kurtaev
adbd613660
Enable Eltwise layer with different numbers of inputs channels
5 years ago
Alexander Alekhin
ab5252c18e
dnn(pytest): backport changes from master, update test setUp()
5 years ago
Dmitry Kurtaev
e35fd463e7
Enable ENet with Inference Engine backend on CPU
5 years ago
Alexander Alekhin
fd11e3a81d
dnn: update IE tests
5 years ago
Alexander Alekhin
f0058bbed3
dnn(test): fix optional test data
5 years ago
Alexander Alekhin
2b66495a9d
dnn: use OpenVINO 2019R3 defines
5 years ago
Alexander Alekhin
8814645c8d
dnn(test): skip IE/OCL test for "sum"
5 years ago
Alexander Alekhin
440a937d24
dnn: increase async test timeout
5 years ago
Dmitry Kurtaev
fba9fdfd27
Fix autodetection of input size for dnn networks
5 years ago
Andrew Ryrie
b88435fdc2
dnn: Allow LSTM layer to operate in reverse direction
...
This is useful for bidirectional LSTMs.
5 years ago
Lubov Batanina
e923712d81
Merge pull request #15572 from l-bat:deconv3d
...
Fix computation of internal shapes in Deconvolution layer
* Fix computation of internal shapes
* Refactoring
5 years ago
Dmitry Kurtaev
b8d4664e6e
Fix OpenVINO 2019R1 compilation
5 years ago
Dmitry Kurtaev
bd5d16ce36
Fix DetectionModel in case of out of [0, 1] range detection prediction
5 years ago
Dmitry Kurtaev
3ddb005480
Fix DetectionModel in case of out of [0, 1] range detection prediction
5 years ago
Dmitry Kurtaev
0428f60d66
Fix OpenVINO 2019R1 compilation
5 years ago
Alexander Alekhin
a0d227714e
dnn: use OpenVINO 2019R3 defines
5 years ago
Dmitry Kurtaev
ba703157cf
Merge pull request #15063 from dkurt:dnn_ie_ocv_layers
...
* Wrap unsupported by IE layers as custom layers
* Replace pointers to layers blobs to their shapes
* Enable Faster R-CNN with IE backend on CPU
5 years ago
Alexander Alekhin
48d41ab088
dnn: bump API version
5 years ago
Alexander Alekhin
70dfae31a2
experimental version++
5 years ago
Lubov Batanina
90eb529bc4
Merge pull request #15395 from l-bat:fully_connected
...
* Fix IE FullyConnected layer
* Fix MyriadX
5 years ago
Dmitry Kurtaev
57676cf64d
Fix https://github.com/opencv/opencv/issues/15141
5 years ago
luz.paz
fcc7d8dd4e
Fix modules/ typos
...
Found using `codespell -q 3 -S ./3rdparty -L activ,amin,ang,atleast,childs,dof,endwhile,halfs,hist,iff,nd,od,uint`
backporting of commit: ec43292e1e
5 years ago
luz.paz
ec43292e1e
Fix modules/ typos
...
Found using `codespell -q 3 -S ./3rdparty -L activ,amin,ang,atleast,childs,dof,endwhile,halfs,hist,iff,nd,od,uint`
5 years ago
Dmitry Kurtaev
e4a80aee09
Fix #15296
5 years ago
Diego
f7f2438478
Merge pull request #15082 from dvd42:segmentation-module
...
Segmentation module (#15082 )
5 years ago
Lubov Batanina
f1ea9d86b9
Merge pull request #15203 from l-bat:determine_inp_shape
...
* Determine input shapes
* Add test
* Remove getInputShapes
* Fix model
* Fix constructors
* Add Caffe test
* Fix predict
5 years ago
Tomoaki Teshima
40c71a2463
suppress noisy warning
...
* add -Wno-psabi when using GCC 6
* add -Wundef for CUDA 10
* add -Wdeprecated-declarations when using GCC 7
* add -Wstrict-aliasing and -Wtautological-compare for GCC 7
* replace cudaThreadSynchronize with cudaDeviceSynchronize
5 years ago
Dmitry Kurtaev
a9839af903
Add preprocessing warps for separate parameters
5 years ago
Dmitry Kurtaev
6193e403e7
Enable some tests for 2019R2
5 years ago
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
5 years ago
Lubov Batanina
778f42ad34
Add high level API (Merge pull request #14780 )
...
* Add high level API
* Fix Model
* Add DetectionModel
* Add ClassificationModel
* Fix classify
* Add python test
* Fix pytest
* Fix comments to review
* Fix detect
* Fix docs
* Modify DetectionOutput postprocessing
* Fix test
* Extract ref boxes
* Fix draw rect
* fix test
* Add rect wrap
* Fix wrap
* Fix detect
* Fix Rect wrap
* Fix OCL_FP16
* Fix MyriadX
* Fix nms
* Fix NMS
* Fix coords
5 years ago
Lubov Batanina
5a6b23e8f3
Support for several min and max sizes in PriorBox layer (Merge pull request #15076 )
...
* Support for several min and max sizes in PriorBox layer
* Fix minSize
* Check size
* Modify initInfEngine
* Fix tests
* Fix IE support
* Add priorbox test
* Remove inputs
5 years ago
Dmitry Kurtaev
f9f160404a
Add support for slice from ONNX with multiple outputs
5 years ago
Dmitry Kurtaev
ebaefbb745
Remove VGG16 from ONNX test because there is VGG16_bn
5 years ago