projects / platform / upstream / nnstreamer.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 31396b1) | patch
[TensorMux] Skeleton for the Tensor Muxer
authorjijoong.moon <jijoong.moon@samsung.com>
Wed, 4 Jul 2018 06:06:27 +0000 (15:06 +0900)
committer함명주/동작제어Lab(SR)/Principal Engineer/삼성전자 <myungjoo.ham@samsung.com>
Wed, 4 Jul 2018 08:20:54 +0000 (17:20 +0900)
commit33c2ff28b96f52101b1306e0388c9228e139e827
tree93a841bc2f558827ae3323cde4fa14ceb4883865tree | snapshot
parent31396b19b5b3c0f2dafff5184cae3a98e2c0070acommit | diff
[TensorMux] Skeleton for the Tensor Muxer

In oder to muxing tensors, we need tensor muxer. It takes as many as
"other/tensor" (currently 16 is max) and make it "other/tensors".
Therefore there are multiple sink pad of tensor and one source pad for
tensors.

Also we may need to enable how we concate the tensor. Maybe direction
property is needed.

- Add CMakeList.txt
- Add gsttensormux.c
- Add gsttensormux.h
- Modify nnstreamer/CMakeList.txt

Signed-off-by: jijoong.moon <jijoong.moon@samsung.com>
CMakeLists.txt diff | blob | history
gst/tensor_mux/CMakeLists.txt [new file with mode: 0644] blob
gst/tensor_mux/gsttensormux.c [new file with mode: 0644] blob
gst/tensor_mux/gsttensormux.h [new file with mode: 0644] blob
Domain: Machine Learning / ML Framework;