Liubov Batanina
9ed1332355
Merge pull request #16722 from l-bat:reshape_opset_11
...
* Supported Div op for constants
* Added Mul test
5 years ago
ashishiva3@gmail.com
e18d5e94c7
Gather-Cast, Mul-Cast fusion
5 years ago
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
5 years ago
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
5 years ago
Liubov Batanina
b1b78aedd2
Skipped ResizeUnfused test on Builder API
5 years ago
ashishiva3@gmail.com
8559237d4e
ONNX: upsample subgraph fusion added
5 years ago
YashasSamaga
98b5fb4b9f
disable MaskRCNN test for CUDA_FP16
5 years ago
Alexander Alekhin
cc0066d38d
dnn(test): adjust check tolerance in Keypoints_face
5 years ago
Dmitry Kurtaev
d8dea7896b
Merge pull request #16628 from dkurt:dnn_ngraph_custom_layers
...
* Custom layers with nGraph
* nGraph: multiple outputs from nodes
5 years ago
Alexander Alekhin
c2f5f5a202
dnn(test): configure filtering for 32-bit systems (part 2)
5 years ago
Alexander Alekhin
d54d01ca46
core(MatExpr): fix .type() bug
5 years ago
Alexander Alekhin
1540ae340f
dnn(test): configure filtering for 32-bit systems
5 years ago
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()
5 years ago
berak
4fdf4d380c
dnn: small fix in pose estimation model
5 years ago
Dmitry Kurtaev
f3eef792eb
Enable Mask R-CNN with Inference Engine. Full coverage with nGraph
5 years ago
Alexander Alekhin
1602a38fa9
Merge pull request #16572 from alalek:dnn_test_dldt_ir_v10
...
* dnn(test): test DLDT IRv10 model, drop old models
* dnn(test): don't expect bitexact results in DLDT IR tests
5 years ago
Liubov Batanina
e970eccbf1
Merge pull request #16472 from l-bat:cp_vton
...
Add CP-VTON sample
* Support resize from PyTorch
* Add CP-VTON sample
* Fix downsampling
* Fix test
* Add model links
* Add default args
* Speed up resize
* Fix TOM link
* Add default args
* Fix comments
* Set aspect ratio for input
* Update links
* Check files exist
5 years ago
Gagandeep Singh
a6f3a21256
Merge pull request #16424 from czgdp1807:issue-16370
...
* fixed Split layer in ONNXImporter
* added test for fix of split layer
* fixed tests for Split layer
* applied reviews
* updated tests
* fixed paths in tests
5 years ago
ashishiva3@gmail.com
cd53144ed3
commit: Corrected end tensor_content parsing for StridedSlice layer.
5 years ago
Alexander Alekhin
8ecfb59930
dnn(test): skip failed ngraph tests
5 years ago
ashishiva3@gmail.com
d64529f6de
Added parsing for Connected and Dropout. Modified maxpool padding
5 years ago
Dmitry Kurtaev
005f38fb45
Fix dnn::ResizeLayer to manage varying input shapes
5 years ago
Alexander Alekhin
b21a861c5b
dnn(test): adjust test tolerance for MYRIAD
5 years ago
ashishiva3@gmail.com
f29bc22005
Convolutional padding parsing modified
5 years ago
Yashas Samaga B L
d85e67d3ec
Merge pull request #16063 from YashasSamaga:cuda4dnn-shortcut-unequal
...
support eltwise sum with different number of input channels in CUDA backend
* add shortcut primitive
* add offsets in shortcut kernel
* skip tests involving more than two inputs
* remove redundant modulus operation
* support multiple inputs
* remove whole file indentation
* skip acc in0 trunc test if weighted
* use shortcut iff channels are unequal
5 years ago
YashasSamaga
fd369a5004
fix and optimize ROIPooling
5 years ago
Dmitry Kurtaev
c1c84d2fd1
ONNX graphs simplifier
5 years ago
Dmitry Kurtaev
8f1e36f7c1
Disable some tests for Myriad target of nGraph
...
Add lightweight IE hardware targets checks
nGraph: Concat with paddings
Enable more nGraph tests
Restore FP32->FP16 for GPU plugin of IE
try to fix buildbot
Use lightweight IE targets check only starts from R4
5 years ago
Liubov Batanina
e9e3af0aaa
Add global pool by axis test
5 years ago
Yashas Samaga B L
1fac1421e5
Merge pull request #16010 from YashasSamaga:cuda4dnn-fp16-tests
...
* enable tests for DNN_TARGET_CUDA_FP16
* disable deconvolution tests
* disable shortcut tests
* fix typos and some minor changes
* dnn(test): skip CUDA FP16 test too (run_pool_max)
5 years ago
Alexander Alekhin
97b6068c46
dnn(test): don't require downloaded data
5 years ago
antalzsiroscandid
aa80f754f4
dnn: reading IR models from buffer
5 years ago
Alexander Alekhin
2c0d9fa81f
dnn(test): fix Test_Model.Keypoints* tests
5 years ago
Xuanda Yang
3d60a9b96c
Merge pull request #16156 from TH3CHARLie:3.4
...
* Eltwise::DIV support in Halide backend
* fix typo
* remove div from generated test suite to pass CI, switching to manual test...
* ensure divisor not near to zero
* use randu
* dnn(test): update test data for Eltwise.Accuracy/DIV layer test
5 years ago
Diego
5b0b59ecfb
Merge pull request #15189 from dvd42:keypoints_module
...
Keypoints module
5 years ago
Alexander Alekhin
5ee7abbe3c
Merge pull request #16088 from alalek:dnn_eltwise_layer_different_src_channels
...
dnn(eltwise): fix handling of different number of channels
* dnn(test): reproducer for Eltwise layer issue from PR16063
* dnn(eltwise): rework support for inputs with different channels
* dnn(eltwise): get rid of finalize(), variableChannels
* dnn(eltwise): update input sorting by number of channels
- do not swap inputs if number of channels are same after truncation
* dnn(test): skip "shortcut" with batch size 2 on MYRIAD targets
5 years ago
YashasSamaga
a91eca6ec2
add DIV support to EltwiseOp
5 years ago
Dmitry Kurtaev
d8e10f3a8d
Enable MaxPooling with indices in Inference Engine
5 years ago
Alexander Alekhin
0dc0bc80ae
dnn(test): fix Vulkan skip test tag
5 years ago
Dmitry Kurtaev
ca1ba7a53d
Backport for dnn input shape estimation
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
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
Dmitry Kurtaev
e35fd463e7
Enable ENet with Inference Engine backend on CPU
5 years ago