experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Fix doc error/typo in using TFLite through C++

Browse Source 
PiperOrigin-RevId: 315855497
Change-Id: If1676c8803259e6f42f7a1468ab8f3a6f2c7f46c
This commit is contained in:
A. Unique TensorFlower 2020-06-11 01:28:48 -07:00 committed by TensorFlower Gardener
parent 236d73ad43
commit fc64c9b00d
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
tensorflow/lite/g3doc/guide/android.md
View File

@ -270,9 +270,10 @@ There are two ways to use TFLite through C++ if you build your app with the NDK:
This is the *recommended* approach. Download the
[TensorFlow Lite AAR hosted at JCenter](https://bintray.com/google/tensorflow/tensorflow-lite),
rename it to `tensorflow-lite-*.zip`, and unzip it. You must include the three
header files in `headers/tensorflow/lite/c/` folder and the relevant
`libtensorflowlite_jni.so` dynamic library in `jni/` folder in your NDK project.
rename it to `tensorflow-lite-*.zip`, and unzip it. You must include the four
header files in `headers/tensorflow/lite/` and `headers/tensorflow/lite/c/`
folder and the relevant `libtensorflowlite_jni.so` dynamic library in `jni/`
folder in your NDK project.
The `c_api.h` header file contains basic documentation about using the TFLite C
API.
@ -297,5 +298,5 @@ bazel build -c opt --config=android_arm64 //tensorflow/lite:libtensorflowlite.so
Currently, there is no straightforward way to extract all header files needed,
so you must include all header files in `tensorflow/lite/` from the TensorFlow
repository. Additionally, you will need header files from
[FlatBUffers](https://github.com/google/flatbuffers) and
[FlatBuffers](https://github.com/google/flatbuffers) and
[Abseil](https://github.com/abseil/abseil-cpp).