Li Peng
145eae321e
pooling ocl kernel optimization
...
set global size with real output size, also optimize
max pooling index computation if necessary.
Signed-off-by: Li Peng <peng.li@intel.com>
7 years ago
Dmitry Kurtaev
d971678add
Add a planar data layout tracking for TensorFlow importer
7 years ago
Dmitry Kurtaev
346871e27f
Set output layers names and types for models in DLDT's intermediate representation
7 years ago
Dmitry Kurtaev
dbeb4a11be
Parse strides and convolution kernel shapes considering data layout
7 years ago
Dmitry Kurtaev
9510551c63
Multiple inputs for TensorFlow models
7 years ago
Dmitry Kurtaev
715f40a48d
Use layers consumers to predict data layout
7 years ago
Li, Peng
ab8022f74e
update convolution opencl kernels in dnn module ( #11762 )
...
* optimize ocl kernel enqueue in fc layer
Signed-off-by: Li Peng <peng.li@intel.com>
* use CV_LOG_INFO in convolution auto tuning
Signed-off-by: Li Peng <peng.li@intel.com>
* update convolution IDLF kernel
extend parameter tuning range, also cleanup
ocl kernel implementation
Signed-off-by: Li Peng <peng.li@intel.com>
* update in-memory convolution cache config
fp16 and fp32 cache config are stored separately
Signed-off-by: Li Peng <peng.li@intel.com>
7 years ago
Dmitry Kurtaev
e8e9d1d021
Implement Interp layer using Resize layer
7 years ago
Alexander Alekhin
50c607d206
dnn(ocl): fix external / predefined builtin configuration behavior
...
OPENCV_OCL4DNN_FORCE_AUTO_TUNING should ignore existed configuration from:
- builtin predefined configurations (for Intel OpenCL iGPUs)
- external configuration (via OPENCV_OCL4DNN_CONFIG_PATH)
Prefer external configuration over builtin.
7 years ago
Dmitry Kurtaev
4626246087
Add ShuffleChannel layer
7 years ago
Dmitry Kurtaev
40b85c1cd9
Remove undocumented feature to retreive layers outputs by indices
7 years ago
Dmitry Kurtaev
bd87eb6e66
Import average pooling and softmax layers from Darknet
7 years ago
Dmitry Kurtaev
693a7663e7
Import ClipByValue from Keras
7 years ago
Alexander Alekhin
5fd7cfbcad
dnn: add runtime parameter OPENCV_DNN_BACKEND_DEFAULT
...
to control DNN_BACKEND_DEFAULT enumeration value behavior
7 years ago
Dmitry Kurtaev
7d727ac2fb
Fuse top layers to batch normalization
7 years ago
Dmitry Kurtaev
2c291bc2fb
Enable FastNeuralStyle and OpenFace networks with IE backend
7 years ago
rockzhan
1187a7fa34
Merge pull request #11649 from rockzhan:dnn_dw_prelu
...
dnn: Fix output mismatch when forward dnn model contain [depthwise conv(group=1) + bn + prelu] (#11649 )
* this can make sure [depthwise conv(group=1) + bn + prelu] output not shift
* add TEST to show the output mismatch in [DWconv+Prelu]
* fix typo
* change loading image to init cvMat directly
* build runtime model, without loading external model
* remove whitespace
* change way to create a cvmat
* add bias_term, add target output
* fix [dwconv + prelu] value mismatch when no optimizations
* fix Test error when change output channels
* add parametric test
* change num_output to group value
* change conv code and change test back
7 years ago
David
7175f257b5
Added ResizeBilinear op for tf ( #11050 )
...
* Added ResizeBilinear op for tf
Combined ResizeNearestNeighbor and ResizeBilinear layers into Resize (with an interpolation param).
Minor changes to tf_importer and resize layer to save some code lines
Minor changes in init.cpp
Minor changes in tf_importer.cpp
* Replaced implementation of a custom ResizeBilinear layer to all layers
* Use Mat::ptr. Replace interpolation flags
7 years ago
Dmitry Kurtaev
f3a6ae5f00
Wrap Inference Engine init to try-catch
7 years ago
Dmitry Kurtaev
b781ac7346
Make Intel's Inference Engine backend is default if no preferable backend is specified.
7 years ago
Kuang Fangjun
9ae28415ec
fix doc.
7 years ago
Dmitry Kurtaev
ab389142af
Fix multiple networks with Intel's Inference Engine backend
7 years ago
Alexander Alekhin
799b4f48e7
fix missing precomp.hpp
7 years ago
Dmitry Kurtaev
32bab45f81
Fix Inference Engine graphs with fused output layers
7 years ago
Dmitry Kurtaev
f96f934426
Update Intel's Inference Engine deep learning backend ( #11587 )
...
* Update Intel's Inference Engine deep learning backend
* Remove cpu_extension dependency
* Update Darknet accuracy tests
7 years ago
Dmitry Kurtaev
bf87a43185
Faster-RCNN object detection models from TensorFlow
7 years ago
Tomoaki Teshima
2e9e71ab9e
make ocl4dnn available to run on other platform than Intel GPU
7 years ago
Dmitry Kurtaev
085be6a445
Fix dilated convolution from Keras
7 years ago
Dmitry Kurtaev
2c3c59d018
Remove Shift deep learning layer
7 years ago
Maksim Shabunin
895e10c317
dnn: fixed IE support on Windows
7 years ago
Alexander Alekhin
471c17321f
improve code quality
...
- eliminate rand() calls
- non initialized members/ variables
- unused return values
- missing/useless NULL checks
7 years ago
Maksim Shabunin
53a68783a5
dnn: support later IE versions
7 years ago
Dmitry Kurtaev
07dc6d2b45
Return a convex hull from rotatedRectangleIntersection
7 years ago
Alexander Alekhin
d6279bfff8
fix build warnings
7 years ago
Li Peng
ba5e8befa9
fp16 ocl support for more layers
...
Signed-off-by: Li Peng <peng.li@intel.com>
7 years ago
Li Peng
3dd916882a
fp16 ocl support for googlenet
...
Signed-off-by: Li Peng <peng.li@intel.com>
7 years ago
Li Peng
329abb5b64
dnn fp16 support
...
Signed-off-by: Li Peng <peng.li@intel.com>
7 years ago
Tomoaki Teshima
3f5347dd7a
work around of the test failure of opencv_test_dnn
...
* let OpenCL kernel run only on Intel GPU
* brush up the workaround based on 9a2b028 from alalek
7 years ago
Dmitry Kurtaev
8488f2e265
EAST: An Efficient and Accurate Scene Text Detector ( https://arxiv.org/abs/1704.03155v2 )
7 years ago
Dmitry Kurtaev
c99c3e761e
Fuse multipliers but not convolution layers weights
7 years ago
Dmitry Kurtaev
777d77848c
Free Convolution and MatMul weights after TensorFlow layers import
7 years ago
Dmitry Kurtaev
9ffe4694db
Reduce memory consumption at Caffe importer
7 years ago
zuoshaobo
4ff6a1bc7b
Merge pull request #11425 from zuoshaobo:relu_negative_slope
...
* FIX INF_ENGINE RELU ERROR
* set slope to variable
* tab in indentwq
7 years ago
Alexander Alekhin
65b0b319eb
eliminate MSVS2017 build warning
...
modules\dnn\src\layers\prior_box_layer.cpp(208): warning C4834: discarding return value of function with 'nodiscard' attribute
7 years ago
Alexander Alekhin
8c349ff8ff
core: added MatSize::dims() method
...
to avoid accessing of 'p[-1]' (static code analysers dislike this)
7 years ago
Alexander Alekhin
576d2dbac0
refactor: don't use CV_ErrorNoReturn() internally
7 years ago
Dmitry Kurtaev
4ec456f0a0
Custom layers for deep learning networks ( #11129 )
...
* Custom deep learning layers support
* Stack custom deep learning layers
7 years ago
Dmitry Kurtaev
d959d7b9f0
Fuse deconvolution layer subgraphs from Keras
7 years ago
Dmitry Kurtaev
bd77d100e1
Enable some tests for clDNN plugin from Intel's Inference Engine
7 years ago
Dmitry Kurtaev
3b4a292ca9
Let switch CPU/OpenCL targets for models from Intel's Model Optimizer
7 years ago