tflite_benchmark_model supports `use_nnapi` parameter. (#2337)
author이상규/동작제어Lab(SR)/Principal Engineer/삼성전자 <sg5.lee@samsung.com>
Mon, 20 Aug 2018 05:29:44 +0000 (14:29 +0900)
committer이춘석/동작제어Lab(SR)/Staff Engineer/삼성전자 <chunseok.lee@samsung.com>
Mon, 20 Aug 2018 05:29:44 +0000 (14:29 +0900)
commitb3cb92f81d2bb23d8956120ad4d80354fdcc4c63
treea0666170f2aad0992e028e59bd36c64c78004172
parentec4ea6a482da92f5335fb325d47e245194dfbc72
tflite_benchmark_model supports `use_nnapi` parameter. (#2337)

Previously tflite_benchmark_model always run models with interpreter only.
Now, it uses nnapi delegate on `use_nnapi=true`

```
LD_LIBRARY_PATH=Product/out/lib Product/out/bin/tflite_benchmark_model \
--graph=../models/mobilenet_quant_v1_224.tflite \
--input_layer="Placeholder" --input_layer_shape="1,224,224,3" \
--num_threads=1 --use_nnapi=true \
```

Note that it is still under development.
Instrument code for each operation is not inserted yet.

Signed-off-by: Sanggyu Lee <sg5.lee@samsung.com>
tools/tflite_benchmark_model/benchmark_tflite_model.cc