gal0is
|
206b546e5a
|
tensroflow support maxpoolgrad
|
5 years ago |
Alexander Alekhin
|
65552bf403
|
dnn: fix build with Vulkan
|
5 years ago |
Dmitry Kurtaev
|
75f4c1abf2
|
Enable some tests for Inference Engine backend
|
5 years ago |
Alexander Alekhin
|
a743de0e24
|
dnn: adjust compilation options
|
6 years ago |
Nuzhny007
|
031e57b359
|
Fixed names conflict with dldt
|
6 years ago |
Dmitry Kurtaev
|
96a2f80bf2
|
Limit number of threads in CPU plugin of IE by OpenCV's getNumThreads
|
6 years ago |
Alexander Alekhin
|
24790e4061
|
Merge pull request #14899 from alalek:dnn_fix_bnll_layer
* dnn: fix BNLLLayer implementation
details: https://github.com/BVLC/caffe/blame/1.0/src/caffe/layers/bnll_layer.cpp#L17
* dnn: enable OCV/OpenCL BNLL layer
|
6 years ago |
Alexander Alekhin
|
333e51b217
|
dnn: configure plugin path for InferenceEngine
|
6 years ago |
Alexander Alekhin
|
f3e9eb3371
|
dnn: both protobuf readers have similar behavior
- ReadProtoFromTextFile
- ReadProtoFromTextBuffer
|
6 years ago |
Feng Chen
|
5620306c70
|
Merge pull request #14845 from vonchenplus:ocv_mirrorpad
* tensorflow support mirror pad
* revert macro define
* revert macro define
* reduce code duplication
* revert macro define
|
6 years ago |
Alexander Alekhin
|
894f208de3
|
dnn(test): replace SkipTestException with tags
|
6 years ago |
Lubov Batanina
|
16294437d5
|
Merge pull request #14833 from l-bat:ocv_eltwise3d
* Support Eltwise3d
* Refactoring
* Fix test
|
6 years ago |
Alexander Alekhin
|
f84b08ff08
|
dnn: bump API version
|
6 years ago |
Alexander Alekhin
|
f5ddaef46b
|
experimental version++
|
6 years ago |
Alexander Alekhin
|
13a782c039
|
test: fix usage of findDataFile()
misused 'optional' mode
|
6 years ago |
Alexander Alekhin
|
95d9cfb5c3
|
static analysis issues
|
6 years ago |
Dmitry Kurtaev
|
dfdc91f8c9
|
dnn: fix MVN layer (issue 14683)
|
6 years ago |
Dmitry Kurtaev
|
eba696a41e
|
Merge pull request #14792 from dkurt:dnn_ie_min_version_r5
* Remove Inference Engine 2018R3 and 2018R4
* Fix 2018R5
|
6 years ago |
Maksim Shabunin
|
d60ac98ef2
|
Limited API support for Python3
|
6 years ago |
Maksim Shabunin
|
10d61a2b44
|
Limited API support for Python3
|
6 years ago |
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
|
6 years ago |
Lubov Batanina
|
3efd2df87f
|
Merge pull request #14682 from l-bat:axpy_layer
* Add Axpy layer
* Fix test
* fix caffe importer
|
6 years ago |
Dmitry Kurtaev
|
9c0af1f675
|
Enable more deconvolution layer configurations with IE backend
|
6 years ago |
Yashas Samaga B L
|
ae279966c2
|
Merge pull request #14660 from YashasSamaga:dnn-cuda-build
add cuDNN dependency and setup build for cuda4dnn (#14660)
* update cmake for cuda4dnn
- Adds FindCUDNN
- Adds new options:
* WITH_CUDA
* OPENCV_DNN_CUDA
- Adds CUDA4DNN preprocessor symbol for the DNN module
* FIX: append EXCLUDE_CUDA instead of overwrite
* remove cuDNN dependency for user apps
* fix unused variable warning
|
6 years ago |
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
|
6 years ago |
Alexander Alekhin
|
52548bde05
|
dnn(test): replace file content reading
|
6 years ago |
Dmitry Kurtaev
|
081d9bc73f
|
Fix Identity Switch from Keras
|
6 years ago |
Alexander Alekhin
|
38a3c1ce6b
|
dnn(test): update test tags for Debug build
|
6 years ago |
LaurentBerger
|
a3be8d7cd7
|
dead link
|
6 years ago |
Lubov Batanina
|
61d3222a22
|
Merge pull request #14537 from l-bat:fix_network_vizualizer
Fix dnn visualizer (#14537)
* Fixed print layer params
* Fix print
|
6 years ago |
Dmitry Kurtaev
|
44d21e5a79
|
Enable Slice layer on Inference Engine backend
|
6 years ago |
Dmitry Kurtaev
|
26e426adb1
|
StridedSlice from TensorFlow
|
6 years ago |
dianlujitao
|
f0f50b757d
|
Fix LogSoftmax for ONNX
Fix wrong indentation as well while at it
|
6 years ago |
Alexander Alekhin
|
132253c9f3
|
dnn: use AsyncArray
|
6 years ago |
Kohei Yoshida
|
7b4aefedea
|
Add support for loading ONNX model from in-memory buffer.
|
6 years ago |
Liubov Batanina
|
dfa753c6b4
|
Support OCV backend
|
6 years ago |
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 |