summaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2020-12-17Merge "Removing unnecessary HTML link for feature/privilege" into tizensubmit/tizen/20210113.040508submit/tizen/20201218.065743accepted/tizen/unified/20201221.122650Hyunsoo Park2-18/+18
2020-12-17Merge "Revert "Add Pose correction API"" into tizenkwang son7-135/+3
2020-12-17Revert "Add Pose correction API"kwang son7-135/+3
This reverts commit 9bf593ba1735c09d9bde22dc7a08e6cb79852639. Reason for revert: <ACR review> Change-Id: I8fa860433d69dc41b63fbe7193986109af1c7649
2020-12-17Revert "Add mv_pose_subtract test"kwang son1-16/+2
This reverts commit 1acdec169b90496b23cf18224e08516d8d1d3e3a. Reason for revert: <INSERT REASONING HERE> Change-Id: I98cb7a4d2e1f2cf3d23c02d3eec949476677bb01
2020-12-17Add mv_pose_subtract testKwang Son1-2/+16
Change-Id: I5fe9047902737d1ca2582c886433e7a826c1ed8f Signed-off-by: Kwang Son <k.son@samsung.com>
2020-12-17Removing unnecessary HTML link for feature/privilegeHyunsoo Park2-18/+18
Change-Id: I74e0ac0e0535f6bdcc794fdf77d1ecc3663b23fc Signed-off-by: Hyunsoo Park <hance.park@samsung.com>
2020-12-16Merge "Add Pose correction API" into tizenkwang son7-3/+135
2020-12-16Add Pose correction APIKwang Son7-3/+135
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>
2020-12-11Fix test result typoKwang Son1-3/+3
Facial -> Pose Change-Id: Idfa0cf10713005616b59cfd6f4e4287e8f62c7cb Signed-off-by: Kwang Son <k.son@samsung.com>
2020-11-30mv_inference: Fix seg. fault issue at ConfigureInputInfo()submit/tizen/20201130.082755submit/tizen/20201130.075203accepted/tizen/unified/20201201.124803Inki Dae1-6/+8
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>
2020-11-10mv_inference: Fix target device configurationsubmit/tizen/20201127.010610submit/tizen/20201125.055433submit/tizen/20201112.235944Inki Dae1-36/+36
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>
2020-11-10mv_inference: Load mlapi specific ini file correctlysubmit/tizen/20201110.032259accepted/tizen/unified/20201112.124203Inki Dae1-4/+8
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>
2020-10-28mv_inference: Call LoadConfigFile functionsubmit/tizen/20201109.053646submit/tizen/20201109.032237submit/tizen/20201104.021236Inki Dae1-1/+7
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>
2020-10-07Fix landmarks to two dimensionstizen_6.0.m2_releasesubmit/tizen_6.0_hotfix/20201103.114802submit/tizen_6.0_hotfix/20201102.192502submit/tizen_6.0/20201029.205102submit/tizen/20201007.030722accepted/tizen/unified/20201007.092257accepted/tizen/6.0/unified/hotfix/20201103.050748accepted/tizen/6.0/unified/hotfix/20201103.003858accepted/tizen/6.0/unified/20201030.121630tizen_6.0_hotfixaccepted/tizen_6.0_unified_hotfixTae-Young Chung4-24/+29
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>
2020-09-22Fix wrong parameter descriptionTae-Young Chung2-55/+55
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>
2020-09-16Remove unnecessary variablessubmit/tizen/20200916.055038accepted/tizen/unified/20200918.123714Tae-Young Chung1-15/+3
Change-Id: I3063d82902e6024022a22dd821a999eaaf9e0e37 Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
2020-09-16MoCap mapping value should be added -1Tae-Young Chung1-1/+1
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>
2020-09-16Remove label parameter from mv_inference_pose_landmark_detected_cbTae-Young Chung7-8/+90
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>
2020-09-08Fix description for html linksubmit/tizen/20200911.033103accepted/tizen/unified/20200914.131443Tae-Young Chung1-5/+5
'#' is used for html link of enum item Change-Id: I3472999c294a504fe37c0223b26b4eafc91b0010 Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
2020-09-03Fix division or modulo by float zeroTae-Young Chung1-3/+5
Change-Id: I857aa3fc409ebb1fbaa35262eb771ebb6c92a700 Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
2020-08-26mv_inference: Add two tensor buffer types supportsubmit/tizen/20200828.100528submit/tizen/20200828.025650accepted/tizen/unified/20200831.002550Inki Dae1-3/+23
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>
2020-08-26mv_inference: set tensor size of tensor info structure correctlyInki Dae1-2/+2
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>
2020-08-20[Release] capi-media-vision-0.6.0-3submit/tizen/20200820.044303accepted/tizen/unified/20200820.133523Tae-Young Chung15-303/+318
Merge branch 'tizen_devel' into tizen
2020-08-20[doc] Fix typos in header filesTae-Young Chung9-219/+219
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>
2020-08-19[Testsuite] replace constant number with ARRAY_SIZE()Tae-Young Chung1-30/+32
Change-Id: I86615bd708f1a26a7b5463b0db06b2ee6239ebbe Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
2020-08-18[Inference] Fix label type of mv_inference_landmark_s from char* to intTae-Young Chung2-3/+3
Change-Id: I1e88e884c164d402391c43214bf9d04d7a463715 Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
2020-08-14[Inference] Fix bug to faultily parse pose and mocap mapping filesTae-Young Chung5-56/+64
Change-Id: If2d4de98ae9d626c9939d009e6df2b7a9d6eda4a Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
2020-08-12Sync to tizen branchTae-Young Chung3-7/+45
Release capi-media-vision-0.6.0 Change-Id: I5202d678a2a949d25a34500179135cf82046522f
2020-08-12[Inference] Add new api mv_inference_pose_landmark_detect() and ↵submit/tizen/20200812.013733accepted/tizen/unified/20200813.015352Tae-Young Chung19-29/+2839
mv_pose_compare() APIs Change-Id: Ib17ebcd8ea506ebaa84c610bf7c0bbeeb6d27656 Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com> (cherry picked from commit 6a7f392fed10c1e7d982540fa76d93d4b5a04d9e)
2020-08-11[Inference] Add new api mv_inference_pose_landmark_detect() and ↵Tae-Young Chung19-29/+2839
mv_pose_compare() APIs Change-Id: Ib17ebcd8ea506ebaa84c610bf7c0bbeeb6d27656 Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
2020-07-21Update backend type descriptionsubmit/tizen/20200810.091902Inki Dae1-0/+17
Change-Id: I2958ba0638e234a3d0582199f8650de81b03be14 Signed-off-by: Inki Dae <inki.dae@samsung.com>
2020-07-08[testsuite] Remove code block of no usesubmit/tizen/20200805.080420submit/tizen/20200713.035755Hyunsoo Park1-7/+4
Change-Id: Ic3ae378576cdc3af828eff014bff6c76848b0276 Signed-off-by: Hyunsoo Park <hance.park@samsung.com>
2020-07-03Merge "mv_inference: Check if backend and device types are valid or not" ↵Inki Dae1-0/+24
into tizen
2020-07-02Fix to return invalid parameter when MV_BARCODE_UNDEFINED is givensubmit/tizen/20200708.035054submit/tizen/20200706.003724submit/tizen/20200702.015201accepted/tizen/unified/20200708.125320Tae-Young Chung1-2/+2
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>
2020-07-01Merge "[Barcode] Add new barcode types" into tizensubmit/tizen/20200701.041707Tae-Young Chung10-23/+140
2020-06-30mv_inference: Check if backend and device types are valid or notInki Dae1-0/+24
Change-Id: I1b94f4c4ea73d5f6a8d75448011e85bdef56e099 Signed-off-by: Inki Dae <inki.dae@samsung.com>
2020-06-26mv_inference: Revert Pose Estimation API supportsubmit/tizen/20200626.070253submit/tizen/20200626.060446submit/tizen/20200626.050805accepted/tizen/unified/20200628.221638Inki Dae7-479/+3
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>
2020-06-26[Barcode] Add new barcode typesTae-Young Chung10-23/+140
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>
2020-06-26mv_inference: Change in-house runtime backend nameInki Dae4-9/+9
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>
2020-06-26test: Do not set array size explictlyInki Dae1-35/+35
Change-Id: Ia8b4c081d74bcb3f36e2469dad96df9d64f0ed62 Signed-off-by: Inki Dae <inki.dae@samsung.com>
2020-06-26mv_inference: Fix tensor data typeInki Dae1-3/+3
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>
2020-06-26test: Add NNFW backend test caseInki Dae1-5/+84
Change-Id: I779467941a3cf5c4fc260e4ad7edb4a97f4558e7 Signed-off-by: Inki Dae <inki.dae@samsung.com>
2020-06-26mv_inference: Do not check a config file in case of NNFW backendInki Dae1-1/+2
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>
2020-06-26mv_inference: fix coding style based on Tizen C++ Coding RuleInki Dae8-4619/+4420
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>
2020-06-26mv_inference: Change MLAPI backend string to "mlapi"Inki Dae1-2/+2
Change-Id: If2d9490d42b575e4fb8eb3fc0c425ba60ce7680c Signed-off-by: Inki Dae <inki.dae@samsung.com>
2020-06-26test: Change a backend type from VIVANTE to MLAPIInki Dae3-3/+3
Change-Id: I7de30aa2ac3dfdd728ceea000b1977106dead403 Signed-off-by: Inki Dae <inki.dae@samsung.com>
2020-06-26test: introduce ARRAY_SIZE macro for code cleanupInki Dae1-12/+13
Change-Id: I8fe39ea830d22fb80efe2c607c6fd6fcf2d846a4 Signed-off-by: Inki Dae <inki.dae@samsung.com>
2020-06-26mv_inference: move tensor buffer declaration to just before usedInki Dae1-2/+4
Change-Id: I6551c9e280c72a30e08e41872908273aa2541df4 Signed-off-by: Inki Dae <inki.dae@samsung.com>
2020-06-26mv_inference: use static_cast instead of normal castInki Dae1-38/+38
Change-Id: Ie39903c4e85338e2d6b3fa38a692496854747010 Signed-off-by: Inki Dae <inki.dae@samsung.com>
2020-06-26Consider tensor filter plugin type for NNFWInki Dae2-0/+3
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>
generated by cgit v1.2.3 (git 2.25.1) at 2024-06-28 02:14:13 +0000