Dmitry Kurtaev
d9bada9867
dnn: EfficientDet
5 years ago
Liubov Batanina
d5e8792f55
Merge pull request #17332 from l-bat:fix_nms
...
Fixed NMSBoxes bug
* Added NMS for each class
* Updated cpp sample
* Fixed errors
* Refactoring
* Added NMS for IE
5 years ago
Liubov Batanina
d991c22090
Merge pull request #16575 from l-bat:flownet2
...
Support FlowNet2 model
* Support DataAugmentation layer
* Fix warnings
* Fix comments
* Support Correlation layer
* TEST
* Support Correlation layer
* Supported Accum and FlowWarp layers
* Supported ChannelNorm layer
* Supported Resample with inputs.size() > 1
* Fixed comments
* Refactoring
* Added tests
* Add resample test
* Added asserts in resize layer
* Updated DataAugmentation layer
* Update convolution layer
* Refactoring
* Fix data augmentation layer
* Fix caffe importer
* Fix resize
* Switch to Mat ptr
* Remove useless resize type
* Used ResizeLayer in Accum
* Split ChannelNormLayer
* Delete duplicate assert
* Add sample
* Fix sample
* Added colormap
5 years ago
Liubov Batanina
c5a2d28367
Determine SSD input shape
5 years ago
Aleksandr Pertovskiy
00b19d6fba
Add text recognition example
5 years ago
jackson0223
d30bc0a4c0
Restore face detection train.prototxt from #9516
5 years ago
Elizarov Ilya
221ddec845
Merge pull request #16554 from ieliz:tracker
...
Added DaSiamRPN tracker
* added DaSiamRPN tracker
* whitespace trouble handled
* Fixes for PR
* Fixes for PR
* Fixes for PR
* added new line in the end of the file and x_crop fix
* removed cxy_wh_2_rect function
* removed loop from sofrmax function
* more detailed discription about absolute paths to onnx models
* removed nested while loop, initialization moved from main tracking loop
* added assert message for small init bb
* initial bounding box on videostream
* selection of initial bounding box improved
* created tracker class, fixed initializing bounding box
* fix round of value
* names fix
* private methods renamed
* names fixed, case for video WIP
* fix case with video
* removed hardcoded size of window
* whitespace fix
* links to models fixed
* bounding box drawing fix
* changes does not required
* code style fixes
* fixes
* frame checker added in tracking loop
* fixed import sys
5 years ago
Dmitry Kurtaev
b927ce18b2
Support for MobileNetV3-SSD from TensorFlow
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
Liubov Batanina
24166ac402
Fix indentation
5 years ago
Liubov Batanina
4a19ac5aca
Move instruction
5 years ago
Liubov Batanina
5790810c3a
Change link
5 years ago
Liubov Batanina
4b35112022
Update sample
5 years ago
Alexander Alekhin
d0e02cccba
samples(dnn): avoid 'async' keyword (Python 3.7+)
5 years ago
Liubov Batanina
832ca0734d
Refactoring
5 years ago
Liubov Batanina
bb91e6999b
Fix demo
5 years ago
Liubov Batanina
ea31a14cc5
Update sample
5 years ago
Dmitry Kurtaev
76cfa65d55
AddV2 from TensorFlow
5 years ago
Liubov Batanina
ffa72fc979
Refactoring
5 years ago
Liubov Batanina
6e33769e56
Add human parsing demo
5 years ago
Alexander Alekhin
a45928045a
Merge pull request #16150 from alalek:cmake_avoid_deprecated_link_private
...
* cmake: avoid deprecated LINK_PRIVATE/LINK_PUBLIC
see CMP0023 (CMake 2.8.12+)
* cmake: fix 3rdparty list
- don't include OpenCV modules
5 years ago
Dmitry Kurtaev
6e14cc2189
Resolve https://github.com/opencv/opencv/issues/15863
5 years ago
Lorenzo Lucignano
c40fbad12e
Samples DNN: tf_text_graph_sd.py loads box coder variance and box NMS params from config file
5 years ago
Alexander Alekhin
0e40c8a031
fix pylint warnings
...
pylint 1.8.3
5 years ago
Dmitry Kurtaev
741aee6901
Fix dnn object detection sample
5 years ago
luz.paz
57ccf14952
FIx misc. source and comment typos
...
Found via `codespell -q 3 -S ./3rdparty,./modules -L amin,ang,atleast,dof,endwhile,hist,uint`
backporting of commit: 32aba5e64b
5 years ago
Dmitry Kurtaev
59864a3bbc
Fix #14993
5 years ago
Dmitry Kurtaev
47c5ee5d9c
Fixes for OpenCV face detection network
5 years ago
Dmitry Kurtaev
a0c3bb70a9
Modify SSD from TensorFlow graph generation script to enable MyriadX
5 years ago
Dmitry Kurtaev
a2125594ea
Fix false positives of face detection network for large faces
5 years ago
LaurentBerger
97681d0607
Add clip to deploy.prototxt
5 years ago
Dmitry Kurtaev
a04ab2298b
Fix JS sample of dnn
5 years ago
Dmitry Kurtaev
411ca87a86
Remove extra ")"
5 years ago
Dmitry Kurtaev
d17d3b66aa
Fix face recognition JS sample
6 years ago
Dmitry Kurtaev
d75a089690
Fix face recognition sample for JS
6 years ago
wenzhao
3f5c85e933
opencv.js: fix the loading issue of opencv.js(WASM) in face recognition
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
Dmitry Kurtaev
26e426adb1
StridedSlice from TensorFlow
6 years ago
Alexander Alekhin
132253c9f3
dnn: use AsyncArray
6 years ago
Alexander Alekhin
18151e79bb
cmake(samples): use LINK_PRIVATE in target_link_libraries
6 years ago
Dmitry Kurtaev
63bb97cc19
Asynchronous C++ sample
6 years ago
Dmitry Kurtaev
c3b0a68a2b
Async mode for dnn's object detection sample
6 years ago
LaurentBerger
fa8e301c69
extends regex matching for conv group of layers
6 years ago
Dmitry Kurtaev
a304069687
Remove preprocessing parameters from README
6 years ago
cftang
98d8436440
fix tf_text_graph_common tensor_content type bug
6 years ago
Dmitry Kurtaev
fe7c93cc05
Fix priors boxes generation in case of non square inputs for TensorFlow SSDs
6 years ago
Dmitry Kurtaev
6ad3bf3130
Enable ResNet-based Mask-RCNN models from TensorFlow Object Detection API
6 years ago
Dmitry Kurtaev
252fd63194
Align TensorFlow and OpenCV paths to create a text graph
6 years ago
Alexander Nesterov
cca2c4b314
Update obj. detect sample
6 years ago
Dmitry Kurtaev
67e6a6077d
Create text graphs for Faster-RCNN from TensorFlow with dilated convolutions
6 years ago