Vadim Pisarevsky
70b893333d
Merge pull request #12130 from dkurt:dnn_ie_mvn
2018-08-06 14:37:46 +00:00
Vadim Pisarevsky
e0c93bcf6c
Merge pull request #12082 from dkurt:dnn_ie_faster_rcnn
2018-08-06 14:28:58 +00:00
Alexander Alekhin
ac4a6aad15
Merge pull request #12050 from alalek:dnn_ocl_avoid_memory_access_violation
2018-08-05 14:47:01 +00:00
Dmitry Kurtaev
be08730cd6
MVN layer using Intel's Inference Engine backend
2018-08-02 17:49:03 +03:00
Dmitry Kurtaev
8e034053af
Faster-RCNN from TensorFlow on CPU with Intel's Inference Engine backend
2018-08-01 11:29:58 +03:00
Alexander Alekhin
814ebe39ae
Merge pull request #12113 from dkurt:dnn_fix_ssd_on_myriad
2018-07-31 14:55:18 +00:00
Maksim Shabunin
7cf52de47e
dnn: modified IE search, R2 compatibility fixed
2018-07-31 14:48:06 +03:00
Dmitry Kurtaev
ed0e79cb61
Add missing parameter to DetectionOutput layer from Intel's Inference Engine
2018-07-31 11:37:45 +03:00
Maksim Shabunin
fb1f12021b
Fixed build with latest IE version
2018-07-27 19:56:35 +03:00
Alexander Alekhin
b597c87bed
dnn(ocl): avoid memory access violation
2018-07-27 15:35:11 +03:00
Alexander Alekhin
2f0fc920dd
Merge pull request #12061 from alalek:dnn_test_skip_checks_only
2018-07-26 15:15:32 +00:00
Alexander Alekhin
9137e2d635
Merge pull request #12060 from alalek:dnn_debug_layers
2018-07-26 15:14:32 +00:00
Alexander Alekhin
c37d1a53b5
Merge pull request #12025 from Triplesalt:tfimport-relu
2018-07-26 15:08:05 +00:00
Triplesalt
9eb79926df
Allow a different input order for Mul+Maximum.
...
Squashed : ReLU operand order tests.
2018-07-26 14:19:11 +02:00
Vadim Pisarevsky
fa466b022d
Merge pull request #12052 from dkurt:dnn_ie_torch_tests
2018-07-26 09:09:35 +00:00
Dmitry Kurtaev
faa6c4e1e1
Faster-RCNN anf RFCN models on CPU using Intel's Inference Engine backend.
...
Enable Torch layers tests with Intel's Inference Engine backend.
2018-07-25 19:04:55 +03:00
Alexander Alekhin
dd8701c1a0
dnn(test): skip checks only for unstable tests
...
but execute tested functions in Layer_Test_Halide/Convolution.Accuracy
2018-07-25 16:55:21 +03:00
Alexander Alekhin
74cf48b5d7
dnn(test): use Backend/Target enums
...
instead of 'int'
2018-07-25 16:55:21 +03:00
Alexander Alekhin
45b5b3c13a
dnn: check layer output for NaN/Inf
2018-07-25 16:25:18 +03:00
Maksim Shabunin
cbb1e867e5
More issues found by static analysis
2018-07-24 16:04:42 +03:00
Alexander Alekhin
8de08e0463
Merge pull request #12021 from dkurt:dnn_ie_tf_ssd
2018-07-24 13:03:41 +00:00
Alexander Alekhin
236f383969
Merge pull request #12037 from dkurt:test_openvino_models
2018-07-24 12:34:04 +00:00
Alexander Alekhin
4283309daa
dnn: update tests for OpenVINO models
2018-07-24 09:41:14 +03:00
Dmitry Kurtaev
28e08ae0bd
Add a sample which tests OpenVINO models
2018-07-23 19:08:51 +03:00
Maksim Shabunin
e0603bb45f
Fixed several issues found by static analysis tools
2018-07-23 17:22:47 +03:00
Alexander Alekhin
ee743afebe
dnn(ocl): don't use getUMat() for long live objects
2018-07-20 17:53:55 +03:00
Maksim Shabunin
a4060e15a4
dnn, IE backend: updated to match new interface
2018-07-19 19:22:23 +03:00
Dmitry Kurtaev
c213a3823e
Run entire SSDs from TensorFlow using Intel's Inference Engine
2018-07-19 17:05:56 +03:00
Dmitry Kurtaev
070393dfda
uint8 inputs for deep learning networks
2018-07-19 14:37:33 +03:00
Alexander Alekhin
6c4f618db5
Merge pull request #11104 from asciian:reading_from_stream
2018-07-17 16:24:06 +00:00
Maksim Shabunin
1da46fe6fb
Fixed issues found by static analysis (mostly DBZ)
2018-07-17 16:14:54 +03:00
Alexander Alekhin
78d07e841d
Merge pull request #11959 from pengli:3.4
2018-07-17 11:20:02 +00:00
Li Peng
f0cadaa6e3
enable concat layer fuse for OCL target
...
Signed-off-by: Li Peng <peng.li@intel.com>
2018-07-17 12:46:16 +08:00
Alexander Alekhin
c9439476da
Merge pull request #11970 from dkurt:dnn_enable_tf_tests
2018-07-16 15:51:27 +00:00
Alexander Alekhin
d6c669f5cf
Merge pull request #11963 from dkurt:dnn_cl_fix_matmul
2018-07-16 11:10:32 +00:00
Dmitry Kurtaev
6eb8faea85
Enable TensorFlow networks tests for different backends and targets
2018-07-13 19:58:56 +03:00
Dmitry Kurtaev
de6f0a537d
Fix fully-connected layer in case of number of rows less than 4
2018-07-13 16:35:37 +03:00
Dmitry Kurtaev
dcc1beb1f8
Clip kernel for OpenCL PriorBox layer
2018-07-13 14:49:13 +03:00
Alexander Alekhin
2508f7f971
dnn(ocl): fix wrong usage of stalled .getMat() pointers
...
Temporary object lifetime must be greater than pointer usage.
2018-07-11 19:11:36 +03:00
Dmitry Kurtaev
8b5f061dae
Replace std::vector<char> to std::vector<uchar> for Java bindings of dnn importers
2018-07-11 18:58:56 +03:00
Alexander Alekhin
999aba3807
Merge pull request #11936 from berak:dnn_shufflelayer_name
2018-07-11 12:01:31 +00:00
Alexander Alekhin
82c7ab0231
Merge pull request #11927 from pengli:3.4
2018-07-11 09:33:24 +00:00
Li Peng
4c5a86828a
Fix gemmlike convolution input reading
...
use vload3 for half3 or float3 input vector reading,
also check read position to see if it exceed input width
Signed-off-by: Li Peng <peng.li@intel.com>
2018-07-11 15:25:21 +08:00
berak
a7b502f04a
dnn: preserve name, type strings for ShuffleLayer
2018-07-11 08:19:23 +02:00
Alexander Alekhin
452fa3011c
dnn(test): drop CV_ENUM for DNNBackend / DNNTarget
2018-07-10 15:12:01 +03:00
Dmitry Kurtaev
d57e5406f0
Add readNet* functions which parse models from byte arrays
2018-07-10 11:12:01 +03:00
Alexander Alekhin
7fe0727930
Merge pull request #11924 from alalek:dnn_ocl_fix_max_pool_forward
2018-07-09 16:25:34 +00:00
Alexander Alekhin
529d38613b
Merge pull request #11923 from alalek:dnn_external_protobuf
2018-07-09 16:07:42 +00:00
Alexander Alekhin
88d56dc700
Merge pull request #11922 from alalek:dnn_test_myriad_check
2018-07-09 16:07:18 +00:00
Alexander Alekhin
b6255ab9e7
dnn(ocl4dnn): fix args for 'max_pool_forward' kernel
2018-07-09 18:02:20 +03:00
