AshihsKrShrivastava
d37180a2c4
modification for upsample node fused from unfused Resize subgraph
5 years ago
Liubov Batanina
8badf7f354
Merge pull request #17112 from l-bat:ie_region
...
* Support nGraph Region
* Support region since OpenVINO 2020.2
* Skip myriad
5 years ago
Dmitry Kurtaev
908bf935f7
Flexible inputs for OpenVINO IR models
5 years ago
Dmitry Kurtaev
5e5385a814
Remove NodeVector for nGraph
5 years ago
Alexander Alekhin
ef68cc3d5f
dnn: use OpenVINO 2020.2 defines
...
original commit: 45263d7642
5 years ago
Ilya Lavrenov
91b0100287
Fixed compilation when NN builder is not built
5 years ago
Dmitry Kurtaev
870a775d7d
Align DLIE and nGraph average pooling layers
5 years ago
Dmitry Kurtaev
d3f9ad1145
Enable ONNX SSD from https://github.com/amdegroot/ssd.pytorch
5 years ago
AshihsKrShrivastava
bef6b6282c
ReflecitonPad2d and ZeroPad2d Subgraph fusion added
5 years ago
Dmitry Kurtaev
21ed892489
Fix Elu import from ONNX
5 years ago
Liubov Batanina
734771418e
Merge pull request #16840 from l-bat:matmul_inputs
...
* Supported FullyConnected layer with two inputs
* Skipped test
* Fix conditions
* Added OpenCL support
* Supported ReduceMean3D
* Supported Expand layer
* Fix warning
* Added Normalize subgraph
* refactoring
* Used addLayer
* Fix check
* Used addLayer
* Skip failed test
* Added normalize1 subgraph
* Fix comments
5 years ago
Liubov Batanina
a448d3a6aa
Fix ENet test with OpenVINO 2020.2
5 years ago
Dmitry Kurtaev
b36eba7fab
Support FusedResizeAndPadConv2D from TensorFlow
5 years ago
Dmitry Kurtaev
8574a757f9
Case sensitive dnn layers types
5 years ago
Alexander Alekhin
e661ad2a67
eliminate build warnings
5 years ago
Dmitry Kurtaev
7e4b2057f2
Import TF2.0 network from Keras
5 years ago
Dmitry Kurtaev
467c3ef0ac
Add checks for LSTM initial h and c
5 years ago
Dmitry Kurtaev
8433620295
Bidirectional LSTM
5 years ago
Pavel Rojtberg
66cf55ea1f
dnn: expose only float variant of NMSBoxes for bindings
...
the float variant was always shadowed by the int version as
Rect2d is implicitly convertible to Rect.
This swaps things which is fine, as the vector of boxes was always
copied and the computation was done in double.
5 years ago
Dmitry Kurtaev
11d565ca62
Fix LSTM from ONNX with batch==1
5 years ago
Dmitry Kurtaev
8d69dbdf49
LSTM from ONNX works
5 years ago
Dmitry Kurtaev
14da5ec311
LSTM scalar
5 years ago
Liubov Batanina
718d7e4b04
Merge pull request #16715 from l-bat:slice_onnx
...
* Support Slice layer with multiple inputs
* Add test
* Supported Resize from PyTorch
* Rewrite test
* Remove Cast layer (supported in #16735 )
* Support ConstantOfShape
* Fix tests
* Fix coments
* Remove useless condition
* Fixed failed tests
5 years ago
Dmitry Kurtaev
7f0d90a525
Fix memory leak in Python custom dnn layers
5 years ago
Liubov Batanina
2645ee90ca
Merge pull request #16735 from l-bat:flatten_const_onnx
...
* Supported Flatten for constant nodes
* Added default axis
* Refactoring
* Refactoring
* Added cast layer
* Fix comments
* Add Cast for layers
5 years ago
Alexander Alekhin
9b64eadcb6
dnn(ie): separate IECore for different devices
...
- HETERO plugin doesn't switch well between devices
5 years ago
Alexander Alekhin
db95aec4a7
dnn(ie): switch to nGraph backend by default
5 years ago
Yashas Samaga B L
490908f0ff
Merge pull request #16436 from YashasSamaga:feature-enetb0-yolo
...
dnn(darknet-importer): add grouped convolutions, sigmoid, swish, scale_channels
* update darknet importer to support enetb0-yolo
* remove dropout (pr16438) and fix formatting
* add test for scale_channels
* disable batch testing for scale channels
* do not set LayerParams::name
* merge all activations into setActivation
5 years ago
NesQl
0bcdf7d03e
Merge pull request #16724 from liqi-c:3.4-tengine
...
* Add Tengine support .
* Modify printf to CV_LOG_WARNING
* a few minor fixes in the code
* Renew Tengine version
* Add header file for CV_LOG_WARNING
* Add #ifdef HAVE_TENGINE in tengine_graph_convolution.cpp
* remove trailing whitespace
* Remove trailing whitespace
* Modify for compile problem
* Modify some code style error
* remove whitespace
* Move some code style problem
* test
* add ios limit and build problem
* Modified as alalek suggested
* Add cmake 2.8 support
* modify cmake 3.5.1 problem
* test and set BUILD_ANDROID_PROJECTS OFF
* remove some compile error
* remove some extra code in tengine
* close test.
* Test again
* disable android.
* delete ndk version judgement
* Remove setenv() call . and add License information
* Set tengine default OFF. Close test .
Co-authored-by: Vadim Pisarevsky <vadim.pisarevsky@gmail.com>
5 years ago
Dmitry Kurtaev
b927ce18b2
Support for MobileNetV3-SSD from TensorFlow
5 years ago
Dmitry Kurtaev
9e332dc5fb
Broadcasting from ONNX
5 years ago
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
Liubov Batanina
b1b78aedd2
Skipped ResizeUnfused test on Builder API
5 years ago
ashishiva3@gmail.com
8559237d4e
ONNX: upsample subgraph fusion added
5 years ago
Dmitry Kurtaev
5bbe116f89
Track Hetero execution for nGraph networks using ngraph::Function
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
ashishiva3@gmail.com
2b96a485e7
Darknet_io: Parsing for cost layer added
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
Dmitry Kurtaev
f3eef792eb
Enable Mask R-CNN with Inference Engine. Full coverage with nGraph
5 years ago
Alexander Alekhin
7ac7aca33b
dnn(caffe): fix net.input_dim handling in Caffe importer
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
Dmitry Kurtaev
9a4cafa319
Resolve #14566
5 years ago
Alexander Alekhin
0a91261c7f
dnn: turn off visibility workaround for OpenVINO 2020.1
5 years ago