Add g3doc for TFLite CMake build
PiperOrigin-RevId: 345141508 Change-Id: I9542ce8624f6522ae3227eeba165502eafefcdb1
This commit is contained in:
Terry Heo
TensorFlower Gardener
parent
2527840a36
commit
cced38dbdb
@ -179,6 +179,9 @@ upper_tabs:
|
||||
path: /lite/guide/build_arm64
|
||||
- title: "Build for Raspberry Pi"
|
||||
path: /lite/guide/build_rpi
|
||||
- title: "Build with CMake"
|
||||
path: /lite/guide/build_cmake
|
||||
status: experimental
|
||||
- title: "Reduce binary size"
|
||||
path: /lite/guide/reduce_binary_size
|
||||
status: experimental
|
||||
|
||||
138
tensorflow/lite/g3doc/guide/build_cmake.md
Normal file
138
tensorflow/lite/g3doc/guide/build_cmake.md
Normal file
@ -0,0 +1,138 @@
|
||||
# Build TensorFlow Lite with CMake
|
||||
|
||||
This page describes how to build and use the TensorFlow Lite library with
|
||||
[CMake](https://cmake.org/) tool.
|
||||
|
||||
The following instructions have been tested on Ubuntu 16.04.3 64-bit PC (AMD64)
|
||||
, TensorFlow devel docker image
|
||||
[tensorflow/tensorflow:devel](https://hub.docker.com/r/tensorflow/tensorflow/tags/)
|
||||
and Windows 10.
|
||||
|
||||
**Note:** This feature is currently experimental and available since version 2.4
|
||||
and may change.
|
||||
|
||||
### Step 1. Install CMake tool
|
||||
|
||||
It requires CMake 3.16 or higher. On Ubuntu, you can simply run the following
|
||||
command.
|
||||
|
||||
```sh
|
||||
sudo apt-get install cmake
|
||||
```
|
||||
|
||||
Or you can follow
|
||||
[the official cmake installation guide](https://cmake.org/install/)
|
||||
|
||||
### Step 2. Clone TensorFlow repository
|
||||
|
||||
```sh
|
||||
git clone https://github.com/tensorflow/tensorflow.git tensorflow_src
|
||||
```
|
||||
|
||||
**Note:** If you're using the TensorFlow Docker image, the repo is already
|
||||
provided in `/tensorflow_src/`.
|
||||
|
||||
### Step 3. Create CMake build directory
|
||||
|
||||
```sh
|
||||
mkdir tflite_build
|
||||
cd tflite_build
|
||||
```
|
||||
|
||||
### Step 4. Run CMake tool with configurations
|
||||
|
||||
#### Release build
|
||||
|
||||
It generates an optimized release binary by default. If you want to build for
|
||||
your workstation, simply run the following command.
|
||||
|
||||
```sh
|
||||
cmake ../tensorflow_src/tensorflow/lite
|
||||
```
|
||||
|
||||
#### Debug build
|
||||
|
||||
If you need to produce a debug build which has symbol information, you need to
|
||||
provide `-DCMAKE_BUILD_TYPE=Debug` option.
|
||||
|
||||
```sh
|
||||
cmake ../tensorflow_src/tensorflow/lite -DCMAKE_BUILD_TYPE=Debug
|
||||
```
|
||||
|
||||
#### Cross-compilation for Android
|
||||
|
||||
You can use CMake to build Android binaries. You need to install
|
||||
[Android NDK](https://developer.android.com/ndk) and provide the NDK path with
|
||||
`-DDCMAKE_TOOLCHAIN_FILE` flag. You also need to set target ABI with
|
||||
`-DANDROID_ABI` flag.
|
||||
|
||||
```sh
|
||||
cmake -DCMAKE_TOOLCHAIN_FILE=<NDK path>/build/cmake/android.toolchain.cmake \
|
||||
-DANDROID_ABI=arm64-v8a ../tensorflow_src/tensorflow/lite
|
||||
```
|
||||
|
||||
#### OpenCL GPU delegate
|
||||
|
||||
If your target machine has OpenCL support, you can use
|
||||
[GPU delegate](https://www.tensorflow.org/lite/performance/gpu) which can
|
||||
leverage your GPU power.
|
||||
|
||||
To configure OpenCL GPU delegate support:
|
||||
|
||||
```sh
|
||||
cmake ../tensorflow_src/tensorflow/lite -DTFLITE_ENABLE_GPU=ON
|
||||
```
|
||||
|
||||
**Note:** It's experimental and available only on master(r2.5) branch. There
|
||||
could be compatbility issues. It's only verified with Android devices and NVidia
|
||||
CUDA OpenCL 1.2.
|
||||
|
||||
### Step 5. Build TensorFlow Lite
|
||||
|
||||
In the tflite_build directory,
|
||||
|
||||
```sh
|
||||
cmake --build . -j
|
||||
```
|
||||
|
||||
**Note:** This generates a static library `libtensorflow-lite.a` in the current
|
||||
directory but the library isn't self-contained since all the transitive
|
||||
dependencies are not included. To use the library properly, you need to create a
|
||||
CMake project. Please refer the
|
||||
["Create a CMake project which uses TensorFlow Lite"](#create_a_cmake_project_which_uses_tensorflow_lite)
|
||||
section.
|
||||
|
||||
### Step 6. Build TensorFlow Lite Benchmark Tool
|
||||
|
||||
In the tflite_build directory,
|
||||
|
||||
```sh
|
||||
cmake --build . -j -t benchmark_model
|
||||
```
|
||||
|
||||
## Create a CMake project which uses TensorFlow Lite
|
||||
|
||||
Here is the CMakeLists.txt of
|
||||
[TFLite minimal example](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/examples/minimal).
|
||||
|
||||
You need to have add_subdirectory() for TensorFlow Lite directory and link
|
||||
`tensorflow-lite` with target_link_libraries().
|
||||
|
||||
```
|
||||
cmake_minimum_required(VERSION 3.16)
|
||||
project(minimal C CXX)
|
||||
|
||||
set(TENSORFLOW_SOURCE_DIR "" CACHE PATH
|
||||
"Directory that contains the TensorFlow project" )
|
||||
if(NOT TENSORFLOW_SOURCE_DIR)
|
||||
get_filename_component(TENSORFLOW_SOURCE_DIR
|
||||
"${CMAKE_CURRENT_LIST_DIR}/../../../../" ABSOLUTE)
|
||||
endif()
|
||||
|
||||
add_subdirectory(
|
||||
"${TENSORFLOW_SOURCE_DIR}/tensorflow/lite"
|
||||
"${CMAKE_CURRENT_BINARY_DIR}/tensorflow-lite" EXCLUDE_FROM_ALL)
|
||||
|
||||
add_executable(minimal minimal.cc)
|
||||
target_link_libraries(minimal tensorflow-lite ${CMAKE_DL_LIBS}
|
||||
```
|
||||
@ -1,92 +1,3 @@
|
||||
# Build TensorFlow Lite with CMake
|
||||
|
||||
This page describes how to build the TensorFlow Lite static library with CMake
|
||||
tool.
|
||||
|
||||
The following instructions have been tested on Ubuntu 16.04.3 64-bit PC (AMD64)
|
||||
, TensorFlow devel docker image and Windows 10.
|
||||
[tensorflow/tensorflow:devel](https://hub.docker.com/r/tensorflow/tensorflow/tags/).
|
||||
|
||||
**Note:** This is an experimental that is subject to change.
|
||||
|
||||
**Note:** The following are not currently supported: iOS, Tests and
|
||||
Host Tools (i.e analysis tools etc.)
|
||||
|
||||
#### Step 1. Install CMake tool
|
||||
|
||||
It requires CMake 3.16 or higher. On Ubuntu, you can simply run the following
|
||||
command.
|
||||
|
||||
```sh
|
||||
sudo apt-get install cmake
|
||||
```
|
||||
|
||||
Or you can follow
|
||||
[the official cmake installation guide](https://cmake.org/install/)
|
||||
|
||||
#### Step 2. Clone TensorFlow repository
|
||||
|
||||
```sh
|
||||
git clone https://github.com/tensorflow/tensorflow.git tensorflow_src
|
||||
```
|
||||
|
||||
**Note:** If you're using the TensorFlow Docker image, the repo is already
|
||||
provided in `/tensorflow_src/`.
|
||||
|
||||
#### Step 3. Create CMake build directory and run CMake tool
|
||||
|
||||
```sh
|
||||
mkdir tflite_build
|
||||
cd tflite_build
|
||||
cmake ../tensorflow_src/tensorflow/lite
|
||||
```
|
||||
|
||||
It generates release binary by default. If you need to produce debug builds, you
|
||||
need to provide '-DCMAKE_BUILD_TYPE=Debug' option.
|
||||
|
||||
```sh
|
||||
cmake ../tensorflow_src/tensorflow/lite -DCMAKE_BUILD_TYPE=Debug
|
||||
```
|
||||
|
||||
If you want to configure Android build with GPU delegate support,
|
||||
|
||||
```sh
|
||||
mkdir tflite_build
|
||||
cd tflite_build
|
||||
cmake -DCMAKE_TOOLCHAIN_FILE=<NDK path>/build/cmake/android.toolchain.cmake \
|
||||
-DANDROID_ABI=arm64-v8a -DTFLITE_ENABLE_GPU=ON ../tensorflow_src/tensorflow/lite
|
||||
```
|
||||
|
||||
|
||||
#### Step 4. Build TensorFlow Lite
|
||||
|
||||
In the tflite_build directory,
|
||||
|
||||
```sh
|
||||
cmake --build . -j
|
||||
```
|
||||
|
||||
Or
|
||||
|
||||
```sh
|
||||
make -j
|
||||
```
|
||||
|
||||
|
||||
**Note:** This should compile a static library `libtensorflow-lite.a` in the
|
||||
current directory.
|
||||
|
||||
|
||||
#### Step 5. Build TensorFlow Lite Benchmark Tool
|
||||
|
||||
In the tflite_build directory,
|
||||
|
||||
```sh
|
||||
cmake --build . -j -t benchmark_model
|
||||
```
|
||||
|
||||
Or
|
||||
|
||||
```sh
|
||||
make benchmark_model -j
|
||||
```
|
||||
Please refer [../../g3doc/guide/build_cmake.md](../../g3doc/guide/build_cmake.md)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user