IVGCVSW-5598 ArmNN Doxygen doc needs update
Signed-off-by: James Ward <james.ward@arm.com>
Change-Id: Iac19640fec7aabdfcbb88a0856d4fce3a15d3f27
diff --git a/docs/00_introduction.dox b/docs/00_introduction.dox
index 6600640..6153b03 100644
--- a/docs/00_introduction.dox
+++ b/docs/00_introduction.dox
@@ -176,36 +176,20 @@
cd ~/armnn-devenv/toolchains
#For Mac OS, change the NDK download link accordingly.
- wget https://dl.google.com/android/repository/android-ndk-r17b-linux-x86_64.zip
- unzip android-ndk-r17b-linux-x86_64.zip
- export NDK=~/armnn-devenv/toolchains/android-ndk-r17b
+ wget https://dl.google.com/android/repository/android-ndk-r20b-linux-x86_64.zip
+ unzip android-ndk-r20b-linux-x86_64.zip
+ export NDK=~/armnn-devenv/toolchains/android-ndk-r20b
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- You may want to append `export NDK=~/armnn-devenv/toolchains/android-ndk-r17b` to your `~/.bashrc` (or `~/.bash_profile` in Mac OS).
-
-### Make a standalone toolchain:
-
- (Requires python if not previously installed: `sudo apt install python`)
-
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~.sh
-
- # Create an arm64 API 26 libc++ toolchain.
- $NDK/build/tools/make_standalone_toolchain.py \
- --arch arm64 \
- --api 26 \
- --stl=libc++ \
- --install-dir=$HOME/armnn-devenv/toolchains/aarch64-android-r17b
- export PATH=$HOME/armnn-devenv/toolchains/aarch64-android-r17b/bin:$PATH
-
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-
- You may want to append `export PATH=$HOME/armnn-devenv/toolchains/aarch64-android-r17b/bin:$PATH` to your `~/.bashrc` (or `~/.bash_profile` in Mac OS).
+ You may want to append `export NDK=~/armnn-devenv/toolchains/android-ndk-r20b` to your `~/.bashrc` (or `~/.bash_profile` in Mac OS).
## <a name="buildBoost">Build the Boost C++ libraries</a>
### Download Boost version 1.64:
+#### <b>Note:</b> as of ArmNN version 20.11, Boost is no longer required to build the core ArmNN code. Boost is, however, still required to build the unit tests.
+
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~.sh
mkdir ~/armnn-devenv/boost
cd ~/armnn-devenv/boost
@@ -258,11 +242,11 @@
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~.sh
- mkdir ~/armnn-devenv/google
+ mkdir -p ~/armnn-devenv/google
cd ~/armnn-devenv/google
git clone https://github.com/google/protobuf.git
cd protobuf
- git checkout -b v3.5.2 v3.5.2
+ git checkout -b v3.12.0 v3.12.0
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -306,12 +290,10 @@
cd ~/armnn-devenv/google/
git clone https://github.com/tensorflow/tensorflow.git
cd tensorflow/
- git checkout a0043f9262dc1b0e7dc4bdf3a7f0ef0bebc4891e
+ git checkout fcc4b966f1265f466e82617020af93670141b009 # Tensorflow version 2.3.1
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- You need tensorflow/contrib/makefile/tf_proto_files.txt from TensorFlow to generate TensorFlow protobuf definitions. This file is not available in TensorFlow master branch.
-
## <a name="buildArmNN">Build ArmNN</a>
### Clone ArmNN source code:
@@ -337,25 +319,30 @@
(Requires CMake if not previously installed: `sudo apt install cmake`)
+ <b>Note: </b> please specify the ANDROID_API version.
+ e.g. for version 27 `export ANDROID_API=27`
+
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~.sh
mkdir ~/armnn-devenv/armnn/build
cd ~/armnn-devenv/armnn/build
- CXX=aarch64-linux-android-clang++ \
- CC=aarch64-linux-android-clang \
+ CXX=aarch64-linux-android${ANDROID_API}-clang++ \
+ CC=aarch64-linux-android${ANDROID_API}-clang \
CXX_FLAGS="-fPIE -fPIC" \
cmake .. \
+ -DCMAKE_ANDROID_NDK=$NDK \
-DCMAKE_SYSTEM_NAME=Android \
+ -DCMAKE_SYSTEM_VERSION=$ANDROID_API \
-DCMAKE_ANDROID_ARCH_ABI=arm64-v8a \
- -DCMAKE_ANDROID_STANDALONE_TOOLCHAIN=$HOME/armnn-devenv/toolchains/aarch64-android-r17b/ \
- -DCMAKE_EXE_LINKER_FLAGS="-pie -llog" \
+ -DCMAKE_SYSROOT=$HOME/android-ndk-r20b/toolchains/llvm/prebuilt/linux-x86_64/sysroot \
+ -DCMAKE_EXE_LINKER_FLAGS="-pie -llog -lz" \
-DARMCOMPUTE_ROOT=$HOME/armnn-devenv/ComputeLibrary/ \
-DARMCOMPUTE_BUILD_DIR=$HOME/armnn-devenv/ComputeLibrary/build \
-DBOOST_ROOT=$HOME/armnn-devenv/boost/install/ \
-DARMCOMPUTENEON=1 -DARMCOMPUTECL=1 -DARMNNREF=1 \
-DTF_GENERATED_SOURCES=$HOME/armnn-devenv/google/tf_pb/ -DBUILD_TF_PARSER=1 \
-DPROTOBUF_ROOT=$HOME/armnn-devenv/google/arm64_pb_install/
- make -j16
+ make -j16
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -371,9 +358,9 @@
adb push libarmnn.so /data/local/tmp/
adb push UnitTests /data/local/tmp/
adb push $NDK/sources/cxx-stl/llvm-libc++/libs/arm64-v8a/libc++_shared.so /data/local/tmp/
- adb push $HOME/armnn-devenv/google/arm64_pb_install/lib/libprotobuf.so /data/local/tmp/libprotobuf.so.15.0.1
- adb shell 'ln -s libprotobuf.so.15.0.1 /data/local/tmp/libprotobuf.so.15'
- adb shell 'ln -s libprotobuf.so.15.0.1 /data/local/tmp/libprotobuf.so'
+ adb push $HOME/armnn-devenv/google/arm64_pb_install/lib/libprotobuf.so /data/local/tmp/libprotobuf.so.3.12.0.0
+ adb shell 'ln -s libprotobuf.so.23.0.0 /data/local/tmp/libprotobuf.so.23'
+ adb shell 'ln -s libprotobuf.so.23.0.0 /data/local/tmp/libprotobuf.so'
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -458,14 +445,14 @@
## <a name="buildProtobuf">Build and install Google's Protobuf library</a>
-### Get protobuf-all-3.5.1.tar.gz from [here](https://github.com/protocolbuffers/protobuf/releases/tag/v3.5.1).
+### Get protobuf-all-3.12.0.tar.gz from [here](https://github.com/protocolbuffers/protobuf/releases/tag/v3.12.0).
### Extract:
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~.sh
- tar -zxvf protobuf-all-3.5.1.tar.gz
- cd protobuf-3.5.1
+ tar -zxvf protobuf-all-3.12.0.tar.gz
+ cd protobuf-3.12.0
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -614,8 +601,8 @@
-DCAFFE_GENERATED_SOURCES=$HOME/armnn-devenv/caffe/build/src \
-DBUILD_CAFFE_PARSER=1 \
-DPROTOBUF_ROOT=$HOME/armnn-devenv/google/x86_64_pb_install/ \
- -DPROTOBUF_LIBRARY_DEBUG=$HOME/armnn-devenv/google/arm64_pb_install/lib/libprotobuf.so.15.0.1 \
- -DPROTOBUF_LIBRARY_RELEASE=$HOME/armnn-devenv/google/arm64_pb_install/lib/libprotobuf.so.15.0.1
+ -DPROTOBUF_LIBRARY_DEBUG=$HOME/armnn-devenv/google/arm64_pb_install/lib/libprotobuf.so.23.0.0 \
+ -DPROTOBUF_LIBRARY_RELEASE=$HOME/armnn-devenv/google/arm64_pb_install/lib/libprotobuf.so.23.0.0
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -631,7 +618,7 @@
### Copy the build folder to an arm64 linux machine
-### Copy the libprotobuf.so.15.0.1 library file to the build folder
+### Copy the libprotobuf.so.23.0.0 library file to the build folder
### cd to the build folder on your arm64 machine and set your LD_LIBRARY_PATH to its current location:
@@ -642,11 +629,11 @@
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-### Create a symbolic link to libprotobuf.so.15.0.1:
+### Create a symbolic link to libprotobuf.so.23.0.0:
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~.sh
- ln -s libprotobuf.so.15.0.1 ./libprotobuf.so.15
+ ln -s libprotobuf.so.23.0.0 ./libprotobuf.so.23
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -728,7 +715,7 @@
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~.sh
- /usr/lib/gcc-cross/aarch64-linux-gnu/5/../../../../aarch64-linux-gnu/bin/ld: warning: libz.so.1, needed by /home/<username>/armNN/usr/lib64/libprotobuf.so.15.0.0, not found (try using -rpath or -rpath-link)
+ /usr/lib/gcc-cross/aarch64-linux-gnu/5/../../../../aarch64-linux-gnu/bin/ld: warning: libz.so.1, needed by /home/<username>/armNN/usr/lib64/libprotobuf.so.23.0.0, not found (try using -rpath or -rpath-link)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/docs/01_parsers.dox b/docs/01_parsers.dox
index 1c52c4a..1af2503 100644
--- a/docs/01_parsers.dox
+++ b/docs/01_parsers.dox
@@ -44,6 +44,7 @@
- Yolov1_tiny.
- Lenet.
- MobileNetv1.
+- SqueezeNet v1.0 and SqueezeNet v1.1
## The Arm NN SDK supports the following machine learning layers for Caffe networks:
@@ -157,6 +158,7 @@
- CONCATENATION, Supported Fused Activation: RELU , RELU6 , TANH, NONE
- CONV_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE
- DEPTHWISE_CONV_2D, Supported Fused Activation: RELU , RELU6 , TANH, NONE
+- DEQUANTIZE
- DIV
- EXP
- FULLY_CONNECTED, Supported Fused Activation: RELU , RELU6 , TANH, NONE
@@ -171,10 +173,12 @@
- NEG
- PACK
- PAD
+- QUANTIZE
- RELU
- RELU6
- RESHAPE
- RESIZE_BILINEAR
+- RESIZE_NEAREST_NEIGHBOR
- SLICE
- SOFTMAX
- SPACE_TO_BATCH
@@ -199,6 +203,15 @@
- [Quantized SSD MobileNet](http://download.tensorflow.org/models/object_detection/ssd_mobilenet_v1_quantized_300x300_coco14_sync_2018_07_18.tar.gz)
- DeepSpeech v1 converted from [TensorFlow model](https://github.com/mozilla/DeepSpeech/releases/tag/v0.4.1)
- DeepSpeaker
+- [DeepLab v3+](https://www.tensorflow.org/lite/models/segmentation/overview)
+- FSRCNN
+- EfficientNet-lite
+- RDN converted from [TensorFlow model](https://github.com/hengchuan/RDN-TensorFlow)
+- Quantized RDN (CpuRef)
+- [Quantized Inception v3](http://download.tensorflow.org/models/tflite_11_05_08/inception_v3_quant.tgz)
+- [Quantized Inception v4](http://download.tensorflow.org/models/inception_v4_299_quant_20181026.tgz) (CpuRef)
+- Quantized ResNet v2 50 (CpuRef)
+- Quantized Yolo v3 (CpuRef)
More machine learning operators will be supported in future releases.
<br/><br/><br/><br/>
@@ -251,6 +264,8 @@
- See the TensorFlow [squeeze documentation](https://www.tensorflow.org/api_docs/python/tf/squeeze) for more information.
- tanh
- See the TensorFlow [tanh documentation](https://www.tensorflow.org/api_docs/python/tf/tanh) for more information.
+- transpose
+ - See the TensorFlow [transpose documentation](https://www.tensorflow.org/api_docs/python/tf/transpose) for more information.
## Partially supported
@@ -283,6 +298,8 @@
- The parser does not support all forms of [broadcast composition](https://www.tensorflow.org/performance/xla/broadcasting), only broadcasting of 4D and 1D tensors. See the TensorFlow [minimum operator documentation](https://www.tensorflow.org/api_docs/python/tf/math/minimum) for more information.
- multiply
- The parser does not support all forms of [broadcast composition](https://www.tensorflow.org/performance/xla/broadcasting), only broadcasting of scalars and 1D tensors. See the TensorFlow [multiply documentation](https://www.tensorflow.org/api_docs/python/tf/multiply) for more information.
+- pack/stack
+ - See the TensorFlow [stack documentation](https://www.tensorflow.org/api_docs/python/tf/stack) for more information.
- pad
- Only supports tf.pad function with mode = 'CONSTANT' and constant_values = 0. See the TensorFlow [pad documentation](https://www.tensorflow.org/api_docs/python/tf/pad) for more information.
- realdiv
@@ -295,9 +312,12 @@
- The parser only supports 2D inputs and does not support selecting the `softmax` dimension. See the TensorFlow [softmax documentation](https://www.tensorflow.org/api_docs/python/tf/nn/softmax) for more information.
- split
- Arm NN supports split along the channel dimension for data formats NHWC and NCHW.
+- strided_slice
+ - See the TensorFlow [strided_slice documentation](https://www.tensorflow.org/api_docs/python/tf/strided_slice) for more information.
- subtract
- The parser does not support all forms of broadcasting [broadcast composition](https://www.tensorflow.org/performance/xla/broadcasting), only broadcasting of scalars and 1D tensors. See the TensorFlow [subtract documentation](https://www.tensorflow.org/api_docs/python/tf/math/subtract) for more information.
+
## Tested networks
Arm tests these operators with the following TensorFlow fp32 neural networks:
diff --git a/docs/02_deserializer_serializer.dox b/docs/02_deserializer_serializer.dox
index 0bd677e..d192ec4 100644
--- a/docs/02_deserializer_serializer.dox
+++ b/docs/02_deserializer_serializer.dox
@@ -60,6 +60,7 @@
- Input
- InstanceNormalization
- L2Normalization
+- Logical
- LogSoftmax
- Lstm
- Maximum
@@ -73,8 +74,10 @@
- Permute
- Pooling2d
- Prelu
+- QLstm
- Quantize
- QuantizedLstm
+- Rank
- Reshape
- Resize
- Slice
@@ -87,6 +90,7 @@
- StridedSlice
- Subtraction
- Switch
+- Transpose
- TransposeConvolution2d
More machine learning layers will be supported in future releases.
@@ -131,12 +135,15 @@
- Dequantize
- DetectionPostProcess
- Division
+- ElementwiseUnary
+- Fill
- Floor
- FullyConnected
- Gather
- Input
- InstanceNormalization
- L2Normalization
+- Logical
- LogSoftmax
- Lstm
- Maximum
@@ -150,9 +157,12 @@
- Permute
- Pooling2d
- Prelu
+- QLstm
- Quantize
- QuantizedLstm
+- Rank
- Reshape
+- Resize
- Rsqrt
- Slice
- Softmax
@@ -165,7 +175,6 @@
- Subtraction
- Switch
- TransposeConvolution2d
-- Resize
More machine learning layers will be supported in future releases.