projects / platform / core / api / mediavision.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: be22b20) | patch
Add pose landmark detection inference with outputmetadata 25/258525/3
authorTae-Young Chung <ty83.chung@samsung.com>
Thu, 20 May 2021 01:12:54 +0000 (10:12 +0900)
committerTae-Young Chung <ty83.chung@samsung.com>
Wed, 30 Jun 2021 09:03:32 +0000 (18:03 +0900)
commitd213865d9e2e8fd6bab3371cf455ba47eec9f779
tree37f908cc14e9961289c6790a5dbf9df3e7dff82ctree | snapshot
parentbe22b20edb3472a06ae33f1b11ffe03248113e3ecommit | diff
Add pose landmark detection inference with outputmetadata

Support models which require heatmap decoding with additional refinement
as well as models which just provide landmark results.

Change-Id: Ic993510d2655d488ea8a43e08a56c13d2f9bc94f
Signed-off-by: Tae-Young Chung <ty83.chung@samsung.com>
include/mv_inference_private.h diff | blob | history
mv_machine_learning/mv_inference/inference/include/Inference.h diff | blob | history
mv_machine_learning/mv_inference/inference/include/PoseDecoder.h diff | blob | history
mv_machine_learning/mv_inference/inference/src/Inference.cpp diff | blob | history
mv_machine_learning/mv_inference/inference/src/PoseDecoder.cpp diff | blob | history
Domain: Multimedia / Media Vision;