Commit Graph

214 Commits

Author SHA1 Message Date
Alexander Alekhin 3165baa1f1 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2018-07-02 14:58:29 +03:00
Dmitry Kurtaev 346871e27f Set output layers names and types for models in DLDT's intermediate representation 2018-06-28 10:21:45 +03:00
Vadim Pisarevsky 5dc0e51682 Merge pull request #11839 from dkurt:dnn_ie_r2 2018-06-27 09:56:02 +00:00
Dmitry Kurtaev dbeb4a11be Parse strides and convolution kernel shapes considering data layout 2018-06-26 16:18:21 +03:00
Dmitry Kurtaev b11e22c25b Update Inference Engine tests 2018-06-26 15:38:08 +03:00
Vadim Pisarevsky e87425f047 Merge pull request #11835 from dkurt:dnn_tf_two_inputs 2018-06-26 12:12:24 +00:00
Dmitry Kurtaev 9510551c63 Multiple inputs for TensorFlow models 2018-06-26 14:03:59 +03:00
Vadim Pisarevsky b80c7bca0d Merge pull request #11826 from dkurt:dnn_tf_data_layouts 2018-06-26 06:36:27 +00:00
Alexander Alekhin b39cd06249 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2018-06-25 22:03:17 +03:00
Dmitry Kurtaev 715f40a48d Use layers consumers to predict data layout 2018-06-25 18:25:40 +03:00
Dmitry Kurtaev e8e9d1d021 Implement Interp layer using Resize layer 2018-06-22 19:26:47 +03:00
Dmitry Kurtaev 4626246087 Add ShuffleChannel layer 2018-06-21 19:10:42 +03:00
Dmitry Kurtaev 40b85c1cd9 Remove undocumented feature to retreive layers outputs by indices 2018-06-20 14:44:21 +03:00
Alexander Alekhin 64f2b1b250 Merge remote-tracking branch 'upstream/3.4' into merge-3.4 2018-06-17 16:26:48 +03:00
Alexander Alekhin 30d4e0261a Merge pull request #11766 from dkurt:dnn_darknet_avgpool_softmax 2018-06-14 13:18:30 +00:00
Dmitry Kurtaev bd87eb6e66 Import average pooling and softmax layers from Darknet 2018-06-14 15:22:08 +03:00
Dmitry Kurtaev 693a7663e7 Import ClipByValue from Keras 2018-06-14 13:30:30 +03:00
Alexander Alekhin 0d6518aaa0 Merge remote-tracking branch 'upstream/3.4' into merge-3.4
OpenCV FFmpeg wrapper download links are preserved from ffmpeg/master branch
2018-06-13 19:34:44 +03:00
Dmitry Kurtaev 2c291bc2fb Enable FastNeuralStyle and OpenFace networks with IE backend 2018-06-09 15:57:12 +03:00
Dmitry Kurtaev 40765c5f8d Enable SSD models from TensorFlow with OpenCL plugin of Intel's Inference Engine 2018-06-08 16:55:21 +03:00
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
2018-06-07 13:45:54 +00:00
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
2018-06-07 16:29:04 +03:00
Dmitry Kurtaev f3a6ae5f00 Wrap Inference Engine init to try-catch 2018-06-07 12:55:52 +03:00
Vadim Pisarevsky 3cbd2e2764 Merge pull request #11650 from dkurt:dnn_default_backend 2018-06-06 09:30:39 +00:00
Alexander Alekhin 6816495bee dnn(test): reuse test/test_common.hpp, eliminate dead code warning 2018-06-05 12:52:53 +03:00
Alexander Alekhin 45dd575ed2 Merge remote-tracking branch 'upstream/3.4' into merge-3.4
Revert "documentation: avoid links to 'master' branch from 3.4 maintenance branch"
This reverts commit 9ba9358ecb.

Revert "documentation: avoid links to 'master' branch from 3.4 maintenance branch (2)"
This reverts commit f185802489.
2018-06-04 19:26:10 +03:00
Dmitry Kurtaev b781ac7346 Make Intel's Inference Engine backend is default if no preferable backend is specified. 2018-06-04 18:31:46 +03:00
Alexander Alekhin 04802e41e9 gtest: support parameters with types from anonymous namespace 2018-06-04 13:30:24 +03:00
Vadim Pisarevsky 3030594665 Merge pull request #11644 from alalek:docs_avoid_master_links_in_3.4-2 2018-06-04 10:19:44 +00:00
Vadim Pisarevsky 055f33ec46 Merge pull request #11657 from dkurt:dnn_ie_multiple_networks 2018-06-04 10:12:46 +00:00
Kuang Fangjun 9ae28415ec fix doc. 2018-06-03 17:44:24 +08:00
Dmitry Kurtaev ab389142af Fix multiple networks with Intel's Inference Engine backend 2018-06-01 14:10:32 +03:00
Alexander Alekhin f185802489 documentation: avoid links to 'master' branch from 3.4 maintenance branch (2)
Other links:
- https://raw.githubusercontent.com/opencv/opencv/master
- https://github.com/opencv/opencv/blob/master
2018-05-31 19:30:56 +03:00
Dmitry Kurtaev 32bab45f81 Fix Inference Engine graphs with fused output layers 2018-05-31 16:21:08 +03:00
Vadim Pisarevsky c58cc4c2ff Merge pull request #11255 from dkurt:dnn_tf_faster_rcnn 2018-05-31 11:07:39 +00:00
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
2018-05-31 14:05:21 +03:00
Dmitry Kurtaev bf87a43185 Faster-RCNN object detection models from TensorFlow 2018-05-30 17:12:36 +03:00
Alexander Alekhin 44572fac44 Merge pull request #11557 from tomoaki0705:relaxIntelOnlyOCL4DNN 2018-05-29 15:25:22 +00:00
Tomoaki Teshima 2e9e71ab9e make ocl4dnn available to run on other platform than Intel GPU 2018-05-29 19:18:10 +09:00
Dmitry Kurtaev 085be6a445 Fix dilated convolution from Keras 2018-05-29 12:15:47 +03:00
Alexander Alekhin 471c17321f improve code quality
- eliminate rand() calls
- non initialized members/ variables
- unused return values
- missing/useless NULL checks
2018-05-22 17:08:31 +03:00
Alexander Alekhin 58c8aefe03 dnn(text): update check threshols
- make green Linux debug/Linux32/Win32 builders
2018-05-22 13:29:31 +03:00
Alexander Alekhin 085b27fc3d Merge pull request #11390 from dkurt:east_text_detection 2018-05-21 13:02:29 +00:00
Li Peng 1b517a45ae add fp16 accuracy and perf test
Signed-off-by: Li Peng <peng.li@intel.com>
2018-05-16 22:45:07 +08:00
Alexander Alekhin 78f205ffa5 python: better Python 3 support 2018-05-11 17:32:04 +03:00
Dmitry Kurtaev 8488f2e265 EAST: An Efficient and Accurate Scene Text Detector (https://arxiv.org/abs/1704.03155v2) 2018-05-11 14:55:42 +03:00
cclauss 8a79b167b8 Define execfile, file, long, raw_input, xrange for Python 3 2018-05-03 09:19:05 +02:00
Dmitry Kurtaev 4ec456f0a0 Custom layers for deep learning networks (#11129)
* Custom deep learning layers support

* Stack custom deep learning layers
2018-04-24 14:59:59 +03:00
Alexander Alekhin 29b4fd2774 Merge pull request #11351 from dkurt:dnn_enable_inf_engine_tests 2018-04-23 09:16:39 +00:00
Dmitry Kurtaev d959d7b9f0 Fuse deconvolution layer subgraphs from Keras 2018-04-20 16:51:38 +03:00