Age | Commit message (Collapse) | Author | Files | Lines |
|
|
|
|
|
This reverts commit 9bf593ba1735c09d9bde22dc7a08e6cb79852639.
Reason for revert: <ACR review>
Change-Id: I8fa860433d69dc41b63fbe7193986109af1c7649
|
|
This reverts commit 1acdec169b90496b23cf18224e08516d8d1d3e3a.
Reason for revert: <INSERT REASONING HERE>
Change-Id: I98cb7a4d2e1f2cf3d23c02d3eec949476677bb01
|
|
Change-Id: I5fe9047902737d1ca2582c886433e7a826c1ed8f
Signed-off-by: Kwang Son <k.son@samsung.com>
|
|
Change-Id: I74e0ac0e0535f6bdcc794fdf77d1ecc3663b23fc
Signed-off-by: Hyunsoo Park <hance.park@samsung.com>
|
|
|
|
mv_pose_subtract function is first part of correction API.
With pose detection, they only get pose similarity score but hard to
know differences between user and bvh skeleton line.
Using mv_pose_subtract help how skeleton should be changed.
Change-Id: I9296c00ae17ef45e3d5b86bafa913ad87974cfc6
Signed-off-by: Kwang Son <k.son@samsung.com>
|
|
Facial -> Pose
Change-Id: Idfa0cf10713005616b59cfd6f4e4287e8f62c7cb
Signed-off-by: Kwang Son <k.son@samsung.com>
|
|
mBackendCapacity will be updated after Bind call
so access to mBackendCapacity shoud be done after the completion
of Binding. This patch makes the Bind callback to be called
before calling ConfigureTargetDevices callback.
Change-Id: If074e4005d03275272dfbce636d947c5d673802a
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
Fixed an issue that target device type isn't updated correctly
when binding a backend engine.
This patch makes the target device configuration to be done
before a backend engine binding is completed because actual target device
configuration to the backend engine is done at binding time.
Change-Id: I24b5779f294abdf8944d4ec0339f1c1282e2156b
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
inference_engine_mlapi_backend.ini file is specific to MLAPI backend.
So load this file only in case that a given backend type is MLAPI.
Change-Id: I385d73d8571b506f8ffa6937985436fe8e18f96a
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
This call updates default tensor filter type for MLAPI
from /etc/inference/inference_engine_mlapi_backend.ini file.
Change-Id: I024160aa01470c52dd579b0a84c9e0052dcd5b7f
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
mv_inference_pose_s composes of number_of_pose and mv_inference_landmark_s.
The mv_inference_landmarks_s should include the pose index as well as landmark index.
So, fix the landmarks from one dimensions to two dimensions.
Change-Id: I68ce167846618487521df5ec92652e944413edf0
Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
|
|
output parameters are described as input and output parameters [in,out]
They are all output parameters and should be described as [out].
Change-Id: I5f20fde143c3eaf4188009c2946874c9cfd0ff3a
Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
|
|
Change-Id: I3063d82902e6024022a22dd821a999eaaf9e0e37
Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
|
|
mv_inference_human_pose_landmark_e starts with value 1.
The MoCap mapping value should start with 1. So,
values should be added -1 to handle the values internally.
Change-Id: I32538230ff8ce85a3709cbdffd0587cdf511c0a9
Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
|
|
and add mv_inference_pose_get_label()
In the callback, the label paramter is a type of integer which is
for only one pose. But, depending on models, it can detect multi poses
and provide multi labels for corresponding poses.
So, remove the parameter. Instead, provide new api
mv_inference_pose_get_label().
Change-Id: Ifa1aa2d1c3782c6cefc58560eb08226189a449ea
Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
|
|
'#' is used for html link of enum item
Change-Id: I3472999c294a504fe37c0223b26b4eafc91b0010
Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
|
|
Change-Id: I857aa3fc409ebb1fbaa35262eb771ebb6c92a700
Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
|
|
This patch adds uint32 and int64 types for tensor data allocation.
And also it fixes an issue which allocates tensor buffer with wrong type
Change-Id: I209b23176cc666a8e3417275baad8d8e3a91eaae
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
size member of inference_engine_tensor_info structure should contain
tensor element count which can be calculated with height * width * channel count
Change-Id: Ia0eaf676bf996caa26dca58f02d26bc2818eff55
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
Merge branch 'tizen_devel' into tizen
|
|
Remove @ref tags in front of API. @ref tag should be used
for GROUP_NAME in documentation.
API should be ended with parenthesis and
handle should be started with '#'
Change-Id: I129aebf548b82091b073108ecafe59aabb8e8967
Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
|
|
Change-Id: I86615bd708f1a26a7b5463b0db06b2ee6239ebbe
Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
|
|
Change-Id: I1e88e884c164d402391c43214bf9d04d7a463715
Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
|
|
Change-Id: If2d4de98ae9d626c9939d009e6df2b7a9d6eda4a
Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
|
|
Release capi-media-vision-0.6.0
Change-Id: I5202d678a2a949d25a34500179135cf82046522f
|
|
mv_pose_compare() APIs
Change-Id: Ib17ebcd8ea506ebaa84c610bf7c0bbeeb6d27656
Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
(cherry picked from commit 6a7f392fed10c1e7d982540fa76d93d4b5a04d9e)
|
|
mv_pose_compare() APIs
Change-Id: Ib17ebcd8ea506ebaa84c610bf7c0bbeeb6d27656
Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
|
|
Change-Id: I2958ba0638e234a3d0582199f8650de81b03be14
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
Change-Id: Ic3ae378576cdc3af828eff014bff6c76848b0276
Signed-off-by: Hyunsoo Park <hance.park@samsung.com>
|
|
into tizen
|
|
MV_BARCODE_UNDEFINED is between valid enumeration range, resulting in
generating unexpected barcode image. So, this patch is to prevent the case
and return error when MV_BARCODE_UNDEFINED is used.
Change-Id: I3df9e5069fdd46fa50d1841a1acad5d863b25fc6
Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
|
|
|
|
Change-Id: I1b94f4c4ea73d5f6a8d75448011e85bdef56e099
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
Pose Estimation API may be changed so this patch
reverts this API support. Pose Estimation API support
will be posted later.
Change-Id: I1aa2bf4bd3cb46a1cf70943e53be47326c79a8e0
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
Add EAN_2, EAN_5, CODE93, CODABAR, DATABAR, DATABAR_EXPAND types
Note that EAN_2 and EAN_5 are add-on type of EAN_8/13.
Change-Id: I479326775e418460c00e663ffe16ccb9c413712a
Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
|
|
Official name of NNFW is ONE(On-device Neural Engine)
so use it instead of NNFW.
Change-Id: If6b6351d312607c3864d1b1817cc8dcbbd019fb7
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
Change-Id: Ia8b4c081d74bcb3f36e2469dad96df9d64f0ed62
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
Output tensor type of Inception v3 model converted to Vivante NPU
is UINT16.
Change-Id: Ic9b568aa42b6e77e63d404688efc59cfa8038266
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
Change-Id: I779467941a3cf5c4fc260e4ad7edb4a97f4558e7
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
NNFW backend doesn't need a config file so skip checking this file.
Change-Id: Ia18b2dee23326a2f07398c69829f80eb48cf8553
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
Tizen C++ Coding Rule:
https://wiki.tizen.org/Native_Platform_Coding_Idiom_and_Style_Guide#C.2B.2B_Coding_Style
Change-Id: Ifdb19e21f9ec67784213218a3f2465312aa43dbe
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
Change-Id: If2d9490d42b575e4fb8eb3fc0c425ba60ce7680c
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
Change-Id: I7de30aa2ac3dfdd728ceea000b1977106dead403
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
Change-Id: I8fe39ea830d22fb80efe2c607c6fd6fcf2d846a4
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
Change-Id: I6551c9e280c72a30e08e41872908273aa2541df4
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
Change-Id: Ie39903c4e85338e2d6b3fa38a692496854747010
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|
|
This patch adds a new backend type for NNFW support via NNStreamer.
MediaVision will support Vivante NPU and NNFW(in-house NN Runtime)
through ML Single API of NNStreamer.
For this, this patch also adds a new member, backend_type, in
inference_engine_config, which is used to let ML Single API of
NNStreamer know which tensor filter - Vivante NPU or NNFW - should be used.
Change-Id: I5d67fcc36d8999513c05590cccb290d07539ab33
Signed-off-by: Inki Dae <inki.dae@samsung.com>
|