Dmitry Kurtaev
6389dfe49c
Fixed DetectionOutput output blob shape
6 years ago
Liubov Batanina
dadb1473c1
Add BatchNorm3d layer
6 years ago
Dmitry Kurtaev
c3b0a68a2b
Async mode for dnn's object detection sample
6 years ago
Dmitry Kurtaev
471b83ccd5
Modify paddings computation for SAME pad mode
6 years ago
Dmitry Kurtaev
adc1ef9308
Fix uint8 input data for Async mode of dnn
6 years ago
Dmitry Kurtaev
a6ed8f268a
Remove extra weights cloning from TensorFlow importer
6 years ago
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
6 years ago
Alexander Alekhin
138a80611c
build: avoid MSVC ICE
6 years ago
Dmitry Kurtaev
9408c3e640
Refactored TensorFlow subgraphs fusion
6 years ago
Dmitry Kurtaev
61b928d9bd
Add an assertion for Async request status
6 years ago
Dmitry Kurtaev
4f6be11c0e
Check if Inference Engine networks are fully supported by backend
6 years ago
Liubov Batanina
45ced8e022
Fix ONNX deconvolution
6 years ago
Dmitry Kurtaev
520e351489
Fix batching in DetectionOutput layer
6 years ago
Dmitry Kurtaev
9b635830bc
Run Reshape layer for const input from ONNX models
6 years ago
Dmitry Kurtaev
a5c92c2029
Merge pull request #13694 from dkurt:dnn_ie_async
...
Asynchronous API from Intel's Inference Engine (#13694 )
* Add forwardAsync for asynchronous mode from Intel's Inference Engine
* Python test for forwardAsync
* Replace Future_Mat to AsyncMat
* Shadow AsyncMat
* Isolate InferRequest callback
* Manage exceptions in Async API of IE
6 years ago
Alexander Alekhin
c667de9b68
dnn: force visibility(default) for IE headers
6 years ago
Dmitry Kurtaev
62d079fa69
Fix Normalize layer for Mac
6 years ago
Alexander Alekhin
3902694075
static scans: preserve namespace name
6 years ago
Dmitry Kurtaev
92cbec6fb1
Fix dnn with IE from GitHub
6 years ago
Dmitry Kurtaev
0cfd95c097
Fix TensorFlow's Squeeze and a new fusion for SoftMax from slim backend
6 years ago
Lubov Batanina
60a841c797
Merge pull request #14255 from l-bat:networks_visualization
...
* Add networks visualization
* Disable CXX11
* Fixed multy inputs support
* Added output shapes
* Added color for DLIE/CPU
* Fixed graph colors
6 years ago
Dmitry Kurtaev
a2bbfa1db5
Enable some tests for Inference Engine 2019R1
6 years ago
Alexander Alekhin
a0a1fb5fec
python: discover tests from module/misc/python/test paths
6 years ago
Dmitry Kurtaev
7ce2397b62
Fix a bug in FusedBatchNorm (TensorFlow) layer importer
6 years ago
Alexander Alekhin
e0841f3d6e
dnn(test-tags): add time / memory tags
6 years ago
Dmitry Kurtaev
ec41a4897a
Remove Switch and Merge nodes from TensorFlow networks
6 years ago
BALACHANDAR S
aa167434e6
Merge pull request #14252 from balachandarsv:master-mac-openvino-support
...
* Mac support for op inference engine
Adding condition to check for mac and add corresponding libraries
* Adding mac support in test cases
6 years ago
103yiran
4bb6edf176
Merge pull request #14117 from 103yiran:103yiran-patch-dnn
...
* Postpone variable definitions
* dnn: reduce scope of 'Mat image' variable
6 years ago
Alexander Alekhin
cafa010389
dnn(test): skip tests
6 years ago
Alexander Alekhin
8bc8a94645
dnn: update DNNTestOpenVINO.models tests
...
- models are moved out from OpenVINO package
- need to download them separatelly
6 years ago
Alexander Alekhin
8483801eab
dnn: use OpenVINO 2019R1 defines
6 years ago
Dmitry Kurtaev
e3286c9055
Enable 1x1 convolution optimization
6 years ago
Dmitry Kurtaev
07655c2b4d
Fix build with IE > 2018R5
6 years ago
zuoshaobo
a34c02a001
add support for tf.add_n operation
6 years ago
Dmitry Kurtaev
144b1f4d9d
Reduce number of tested models from OpenVINO
6 years ago
Alexander Alekhin
fcb07c64f3
cmake: fix build of dnn tests with shared common code
...
- don't share .cpp files (PCH support is broken)
6 years ago
Sayed Adel
de22442046
dnn:perf add missing definition __OPENCV_TEST to fix pch
6 years ago
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
6 years ago
Alexander Alekhin
e8c20bfae6
dnn: fix support drop for IE<2018R3
...
- fix build with IE 2018R3
6 years ago
Dmitry Kurtaev
9cfd219d70
Fix Mobilenet v2 from TensorFlow slim
6 years ago
Kohei Yoshida
212420516f
Add a test case for handling output_shape property for deconvolution layer.
6 years ago
Kohei Yoshida
3bcff7f941
Make use of explicit output shape for the de-convolution layer.
...
This is relevant to cases where the net is loaded from an ONNX model
containing ConvTranspose layers, which may include the output_shape
attribute.
c.f. https://github.com/onnx/onnx/blob/master/docs/Operators.md#ConvTranspose
6 years ago
Dmitry Kurtaev
714b38360f
Extend LRN layer support with IE backend
6 years ago
zuoshaobo
8b52eabd48
fix the region layer's output anchor size normalization error
6 years ago
Easton Liu
fcfb29766b
Add ability to read thresh and nms_threshold from YOLO layer in YOLOV3 cfg file.
...
Currently the thresh is hard-coded to be 0.2 and nms_threshold as 0.4.
6 years ago
Alexander Nesterov
74574dfae4
Added optimization fuse
6 years ago
Alexander Alekhin
80d37ba698
dnn: fix usage of CV_LOG_VERBOSE macro
6 years ago
Dmitry Kurtaev
20400aa9f7
Import Upsample and Unsqueeze from ONNX
6 years ago
Dmitry Kurtaev
4cbd09c41c
Add extra limitations for LRN from Inference Engine backend
6 years ago
Dmitry Kurtaev
ed710eaa1c
Make Inference Engine R3 as a minimal supported version
6 years ago