projects / platform / upstream / nnstreamer.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 5d910b4) | patch
[Filter/TF-Lite] update the methods for get in/out dimension of tensors
authorHyoungjooAhn <hello.ahn@samsung.com>
Wed, 18 Jul 2018 07:48:17 +0000 (16:48 +0900)
committer함명주/동작제어Lab(SR)/Principal Engineer/삼성전자 <myungjoo.ham@samsung.com>
Thu, 19 Jul 2018 06:20:24 +0000 (15:20 +0900)
commit5926a2612af40cb328cc2e329fbf352a28147ab0
treeb439a3de8c0ca30b4cc23b61b74199b006eb9530tree | snapshot
parent5d910b43807ac6430c133af00e018a95447ed7aacommit | diff
[Filter/TF-Lite] update the methods for get in/out dimension of tensors

1. by using memcpy, improve the robustness
2. when upper layer call get in/output tensor dimension, return data type of tensor rather than length. because the length is fixed with NNS_TENSOR_RANK_LIMIT

Signed-off-by: HyoungjooAhn <hello.ahn@samsung.com>
gst/tensor_filter/tensor_filter_tensorflow_lite_core.cc diff | blob | history
include/tensor_filter_tensorflow_lite_core.h [moved from gst/tensor_filter/tensor_filter_tensorflow_lite_core.h with 84% similarity] diff | blob | history
Domain: Machine Learning / ML Framework;