Content Comparison

ArmNN SDK ENV variable set:

export BASEDIR=~/armnn-pi

export PATH=$BASEDIR/boost.build/bin:$PATH

export PATH=$BASEDIR/protobuf-host/bin:$PATH

export LD_LIBRARY_PATH=$BASEDIR/protobuf-host/lib:$LD_LIBRARY_PATH

export LD_LIBRARY_PATH=$BASEDIR/armnn/build:$LD_LIBRARY_PATH

export ARMNN_INCLUDE=$BASEDIR/armnn/include

export ARMNN_LIB=$BASEDIR/armnn/build

1. Arm Compute Library

It is in $BASEDIR/ComputeLibrary
It's library built is in $BASEDIR/ComputeLibrary/build

1.1 Running a DNN with random weights and inputs

Arm compute library comes with examples for most common DNN architectures like: AlexNet, MobileNet, ResNet, Inception v3, Inception v4, Squeezenet, etc.
All available examples source code can be found in this example location: $BASEDIR/ComputeLibrary/example .
All available examples can be found in this example build location:
$BASEDIR/ComputeLibrary/build/example
Each model architecture can be tested with graph_[dnn_model] application. For example, to run the MobileNet v2 DNN model with random weights, run the example application without any argument:

Export LD_LIBRARY_PATH=$BASEDIR/ComputeLibrary/build:$LD_LIBRARY_PATH
./graph_mobilenet_v2 The application will create the DNN with random weights and run it with random inputs. If inference finishes, the "Test passed" message should be printed. 1.2 Running AlexNet using graph API Download the archive file to the example location folder from this link: cd $BASEDIR/ComputeLibrary/build/examples _curl -L -o computer_library_alexnet.zip https://developer.arm.com/-/media/Arm%20Developer%20Community/Images/Tutorial%20Guide%20Diagrams%20and%20Screenshots/Machine%20Learning/Running%20AlexNet%20on%20Pi%20with%20Compute%20Library/compute_library_alexnet.zip?revision=c1a232fa-f328-451f-9bd6-250b83511e01_ Create a new sub-folder and unzip the file. mkdir assets_alexnet unzip compute_library_alexnet.zip -d assets_alexnet Set environment variables for execution: export LD_LIBRARY_PATH=$BASEDIR/ComputeLibrary/build/examples:$LD_LIBRARY_PATH export PATH_ASSETS=$BASEDIR/ComputeLibrary/build/examples/assets_alexnet Run the program. ./graph_alexnet --data=$PATH_ASSETS --image=$PATH_ASSETS/go_kart.ppm --labels=$PATH_ASSETS/labels.txt Running Arm NN tests Note that input data, model configurations, and model weights are not distributed with Arm NN. The user must download them separately and make sure they are available on the device before running the tests. However, Arm NN tests don't come with an documentation. Input file names are hardcoded, so investigate the code to find out what input file names are expected. Following sections provide details about how to prepare the input data and how to run Arm NN tests. All of them use well known neural network models, therefore, with only few exceptions, such pre-trained networks are available freely on the Internet. Input images, models, formats and their content was deduced using code analysis. Arm NN test source code is in $BASEDIR/armnn/tests Arm NN test binary code is in $BASEDIR/armnn/build/tests General work-flow is first to prepare data on a host machine and then to deploy it on the board, where the actual Arm NN tests will be run. The following sections assume that neural network model files are stored in a folder called models and input image files are stored in a folder called data. Both of them are created inside a folder called ArmnnTests. Create this folder structure on the larger partition using the following commands: mkdir ArmnnTests cd ArmnnTests mkdir data mkdir models export PATH=$BASEDIR/armnn/build/tests:$PATH 2.1 Caffe tests Arm NN SDK provides the following set of tests for Caffe models: pi@raspberrypi:~/armnn-pi/armnn/build/tests$ ls -l	grep "Caff" -rwxr-xr-x 1 pi pi 915248 Sep 2 05:51 CaffeAlexNet-Armnn -rwxr-xr-x 1 pi pi 725688 Sep 2 05:23 CaffeCifar10AcrossChannels-Armnn -rwxr-xr-x 1 pi pi 915252 Sep 2 05:41 CaffeInception_BN-Armnn -rwxr-xr-x 1 pi pi 729920 Sep 2 05:49 CaffeMnist-Armnn -rwxr-xr-x 1 pi pi 915236 Sep 2 05:15 CaffeResNet-Armnn -rwxr-xr-x 1 pi pi 915248 Sep 2 05:33 CaffeVGG-Armnn -rwxr-xr-x 1 pi pi 920148 Sep 2 05:43 CaffeYolo-Armnn Two important limitations might require preprocessing of the Caffe model file prior to running an Arm NN Caffe test. First, Arm NN tests require batch size to be set to 1. Second, Arm NN does not support all Caffe syntaxes, therefore some older neural network model files will require updates to the latest Caffe syntax. For example, if a Caffe model has a batch size different from one or uses an older Caffe version defined by files model_name.prototxt and model_name.caffemodel, create a copy of the .prototxt file (new_model_name.prototxt), modify this file to use the new Caffe syntax and change the batch size to 1 and finally run the following python script: import caffe net = caffe.Net('model_name.prototxt', 'model_name.caffemodel', caffe.TEST) new_net = caffe.Net('new_model_name.prototxt', 'model_name.caffemodel', caffe.TEST) new_net.save('new_model_name.caffemodel') CaffeAlexNet-Armnn Use A linux host with py-caffe installed Download the model files: cd ~/ArmnnTests curl -L -o deploy.prototxt https://raw.githubusercontent.com/BVLC/caffe/master/models/bvlc_alexnet/deploy.prototxt curl -L -o bvlc_alexnet.caffemodel http://dl.caffe.berkeleyvision.org/bvlc_alexnet.caffemodel cp deploy.prototxt bvlc_alexnet_1.prototxt nano bvlc_alexnet_1.prototxt
name: "AlexNet"
layer {
name: "data"
type: "Input"
top: "data"
input_param { shape: { dim: 1 dim: 3 dim: 227 dim: 227 } }





name: "AlexNet"
layer {
name: "data"
type: "Input"
top: "data"
input_param { shape: { dim: 10 dim: 3 dim: 227 dim: 227 } }

change the batch size to 1

Run the following python script to transform the network
python3
import caffe
net = caffe.Net('deploy.prototxt', 'bvlc_alexnet.caffemodel', caffe.TEST)
new_net = caffe.Net('bvlc_alexnet_1.prototxt', 'bvlc_alexnet.caffemodel', caffe.TEST)
new_net.save('bvlc_alexnet_1.caffemodel')

Copy bvlc_alexnet_1.caffemodel from linux host to ~/ArmnnTests/models in SP7021

Find a .jpg file containing a shark (great white shark). Rename it to shark.jpg and copy it to the data folder on the device.
Run the test

CaffeAlexNet-Armnn --data-dir=data --model-dir=models
1. 1. CaffeInception_BN-Armnn
Use A linux host with py-caffe installed

Download the model files:
cd ~/ArmnnTests
curl -L -o deploy.prototxt https://raw.githubusercontent.com/pertusa/InceptionBN-21K-for-Caffe/master/deploy.prototxt
curl -L -o Inception21k.caffemodel http://www.dlsi.ua.es/~pertusa/deep/Inception21k.caffemodel
cp deploy.prototxt Inception-BN-batchsize1.prototxt
nano Inception-BN-batchsize1.prototxt
name: "Inception21k"

layer {

name: "data"

type: "Input"

top: "data"

input_param { shape: { dim: 1 dim: 3 dim: 224 dim: 224 } }

change the batch size to 1
name: "Inception21k"

layer {

name: "data"

type: "Input"

top: "data"

input_param { shape: { dim: 10 dim: 3 dim: 224 dim: 224 } }

224 } }

Run the following python script to transform the network
import caffe
net = caffe.Net('deploy.prototxt', 'Inception21k.caffemodel', caffe.TEST)
new_net = caffe.Net('Inception-BN-batchsize1.prototxt', 'Inception21k.caffemodel', caffe.TEST)
new_net.save(' Inception-BN-batchsize1.caffemodel')python3

Copy Inception-BN-batchsize1.caffemodel to ~/ArmnnTests/models in SP7021
Find a .jpg file containing a shark (great white shark). Rename it to shark.jpg and copy it to the data folder on the SP7021.
Run the test

CaffeInception_BN-Armnn --data-dir=data --model-dir=models

2.1.3 CaffeMnist-Armnn

Use A linux host with py-caffe installed

Download the model files:
cd ~/ArmnnTests
curl -L -o lenet.prototxt https://raw.githubusercontent.com/BVLC/caffe/master/examples/mnist/lenet.prototxt
curl -L -o lenet_iter_9000_ori.caffemodel https://github.com/ARM-software/ML-examples/blob/master/armnn-mnist/model/lenet_iter_9000.caffemodel
cp lenet.prototxt lenet_iter_9000.prototxt
nano lenet_iter_9000.prototxt
change the batch size to 1

name: "LeNet"
layer {
name: "data"
type: "Input"
top: "data"
input_param { shape: { dim: 1 dim: 1 dim: 28 dim: 28 } }




name: "LeNet"
layer {
name: "data"
type: "Input"
top: "data"
input_param { shape: { dim: 64 dim: 1 dim: 28 dim: 28 } }

Run the following python script to transform the network
python3
import caffe
net = caffe.Net(lenet.prototxt', lenet_iter_9000_ori.caffemodel', caffe.TEST)
new_net = caffe.Net(' lenet_iter_9000.prototxt', lenet_iter_9000_ori.caffemodel', caffe.TEST)
new_net.save(' lenet_iter_9000.caffemodel')

|
Copy lenet_iter_9000.caffemodel to ~/ArmnnTests/models in SP7021

Find a .jpg file containing a shark (great white shark). Rename it to shark.jpg and copy it to the data folder on SP7021.
Download the two archives below and unpack them:

...

TfInceptionV3-Armnn --data-dir=data --model-dir=models

This is not an execution error. This occurs because the TfInceptionV3-Armnn test expects a specific type of dog, cat and shark to be found so if a different type/breed of these animals is passed to the test, it returns a case failed.
The expected inputs for this test are:

ID	Label	File name
208	Golden Retriever	Dog.jpg
283	Tiger Cat	Cat.jpg
3	White Shark	shark.jpg

The complete list of supported objects can be found in https://github.com/ARM-software/armnn/blob/branches/armnn_18_11/tests/TfLiteMobilenetQuantized-Armnn/labels.txt

1. 1. TfMnist-Armnn
Download the model files and copy file to action folder :

...

mv t10k-images-idx3-ubyte t10k-images.idx3-ubyte
mv t10k-labels-idx1-ubyte t10k-labels.idx1-ubyte
cp t10k-images-idx3-ubyte ./data/
cp t10k-labels-idx1-ubyte ./data/

Run the test:

1. 1. TfMobileNet-Armnn
Download and unpack the model file:

...

TfMobileNet-Armnn --data-dir=data --model-dir=models

1. TensorFlow Lite tests

Arm NN SDK provides the following test for TensorFlow Lite models:
pi@raspberrypi:~/ArmnnTests$ ls -l ~/armnn-pi/armnn/build/tests/ | grep "TfL"
-rwxr-xr-x 1 pi pi 919808 Sep 2 05:08 TfLiteInceptionV3Quantized-Armnn
-rwxr-xr-x 1 pi pi 919808 Sep 2 05:28 TfLiteInceptionV4Quantized-Armnn
-rwxr-xr-x 1 pi pi 919656 Sep 2 05:42 TfLiteMnasNet-Armnn
-rwxr-xr-x 1 pi pi 921120 Sep 2 05:29 TfLiteMobilenetQuantized-Armnn
-rwxr-xr-x 1 pi pi 919812 Sep 2 05:14 TfLiteMobileNetQuantizedSoftmax-Armnn
-rwxr-xr-x 1 pi pi 915588 Sep 2 05:20 TfLiteMobileNetSsd-Armnn
-rwxr-xr-x 1 pi pi 919808 Sep 2 05:15 TfLiteMobilenetV2Quantized-Armnn
-rwxr-xr-x 1 pi pi 919808 Sep 2 05:02 TfLiteResNetV2-50-Quantized-Armnn
-rwxr-xr-x 1 pi pi 919656 Sep 2 05:06 TfLiteResNetV2-Armnn
-rwxr-xr-x 1 pi pi 919800 Sep 2 05:42 TfLiteVGG16Quantized-Armnn
-rwxr-xr-x 1 pi pi 666068 Sep 2 05:23 TfLiteYoloV3Big-Armnn
2.3.1 TfLiteInceptionV3Quantized-Armn

...

TfLiteInceptionV3Quantized-Armnn --data-dir=data --model-dir=models

1. 1. TfLiteMnasNet-Armnn
Download and unpack the model file:

...

TfLiteMnasNet-Armnn --data-dir=data --model-dir=models

1. 1. TfLiteMobilenetQuantized-Armnn
Download the model file:

...

TfLiteMobilenetQuantized-Armnn --data-dir=data --model-dir=models

1. 1. TfLiteMobilenetV2Quantized-Armnn
Download the model file:

...

TfLiteMobilenetV2Quantized-Armnn --data-dir=data --model-dir=models

1. ONNX tests

The Arm NN provides the following set of tests for ONNX models:
pi@raspberrypi:~/ArmnnTests$ ls -l ~/armnn-pi/armnn/build/tests/ | grep "Onn"
-rwxr-xr-x 1 pi pi 729136 Sep 2 05:08 OnnxMnist-Armnn
-rwxr-xr-x 1 pi pi 915132 Sep 2 05:01 OnnxMobileNet-Armnn
2.4.1 OnnxMnist-Armnn
1. Download and unpack the model file:
cd ~/ArmnnTests
curl -L -o mnist.tar.gz https://onnxzoo.blob.core.windows.net/models/opset_8/mnist/mnist.tar.gz
tar zxvf mnist.tar.gz

...

OnnxMnist-Armnn --data-dir=data --model-dir=models

1. 1. OnnxMobileNet-Armnn
Download and unpack the model file:

...

OnnxMobileNet-Armnn --data-dir=data --model-dir=models

3. Python interface to Arm NN (PyArmNN)
cd ~/armnn-pi/armnn/python/pyarmnn/examples/
python3 tflite_mobilenetv1_quantized.py

python3 onnx_mobilenetv2.py

Anchor

	_GoBack
	_GoBack

Version	Old Version 1	New Version 2
Changes made by	akira.yu	akira.yu
Saved on	Oct 12, 2020	Oct 12, 2020

Versions Compared

Key

name: "Inception21k"
layer {
name: "data"
type: "Input"
top: "data"
input_param { shape: { dim: 1 dim: 3 dim: 224 dim: 224 } }