[Filter/TF] support string type
authorJaeyun <jy1210.jung@samsung.com>
Fri, 15 Feb 2019 05:03:39 +0000 (14:03 +0900)
committerMyungJoo Ham <myungjoo.ham@samsung.com>
Thu, 21 Feb 2019 17:13:52 +0000 (02:13 +0900)
commitc5f1982b1083b63d977cf38a4ec68ceb0278d0fd
treeba39563b7d92a18924aa2fa0335534d51101a408
parentc3269d7a5df4008e5b504d066c56e08fcb324726
[Filter/TF] support string type

In tensorflow sub-plugin, support DT_STRING type.
Added testcase with speech command model, which classifies wav input to keyword.
This model has input type DT_STRING.

Signed-off-by: Jaeyun Jung <jy1210.jung@samsung.com>
ext/nnstreamer/tensor_filter/tensor_filter_tensorflow_core.cc
tests/nnstreamer_filter_tensorflow/data/2.wav [new file with mode: 0644]
tests/nnstreamer_filter_tensorflow/runTest.sh
tests/test_models/models/conv_actions_frozen.pb [new file with mode: 0644]