Installing TensorFlow for the NPU on the Orange Pi 4B
Install dependencies
sudo apt install python3-pip
pip3 -V
pip 18.1 from /usr/lib/python3/dist-packages/pip (python 3.7)
Download and install TensorFlow
curl "https://github.com/lhelontra/tensorflow-on-arm/releases/download/v1.14.0/tensorflow-1.14.0-cp27-none-linux_aarch64.whl" --output tensorflow-1.14.0-cp27-none-linux_aarch64.whl
pip3 install tensorflow-1.14.0-cp27-none-linux_aarch64.whl
fonctionne pas, pas bonne version de python
git clone https://github.com/lhelontra/tensorflow-on-arm.git
621 cd tensorflow-on-arm/
apt-get install openjdk-11-jdk automake autoconf
610 apt-get install curl zip unzip libtool swig libpng-dev zlib1g-dev pkg-config git g++ wget xz-utils
611 pip install -U keras_applications==1.0.5 --no-deps
612 pip install -U keras_preprocessing==1.0.3 --no-deps
613 apt-get install python3-numpy python3-dev python3-pip python3-mock
apt-get install libpython3-all-dev:armhf
cd build_tensorflow/
chmod +x build_tensorflow.sh
Bon finalement Bazel prend des plombes et rien ne semble s’installer… Du coup, comme je suis en python 3.7, je tente celle là: https://github.com/lhelontra/tensorflow-on-arm/releases/download/v1.14.0-buster/tensorflow-1.14.0-cp37-none-linux_aarch64.whl
poddingue@orangepi4-armbian:~$ sudo -EH python3 -m pip install tensorflow-1.14.0-cp37-none-linux_aarch64.whl
tensorboard 1.14.0 has requirement setuptools>=41.0.0, but you’ll have setuptools 40.8.0 which is incompatible.
poddingue@orangepi4-armbian:~$ sudo -EH python3 -m pip install setuptools –upgrade
Collecting setuptools Downloading https://files.pythonhosted.org/packages/41/fa/60888a1d591db07bc9c17dce2bcfb9f00ac507c0a23ecb827e76feb8f816/setuptools-49.1.0-py3-none-any.whl (789kB) 100% |████████████████████████████████| 798kB 615kB/s Installing collected packages: setuptools Found existing installation: setuptools 40.8.0 Not uninstalling setuptools at /usr/lib/python3/dist-packages, outside environment /usr Can’t uninstall ‘setuptools’. No files were found to uninstall. Successfully installed setuptools-49.1.0 poddingue@orangepi4-armbian:~$
Successfully installed h5py-2.10.0 keras-applications-1.0.8 keras-preprocessing-1.1.2 tensorflow-1.14.0
Launch python3, and see if you can import TensorFlow:
python3
Python 3.7.3 (default, Dec 20 2019, 18:57:59) [GCC 8.3.0] on linux Type “help”, “copyright”, “credits” or “license” for more information.
import tensorflow quit()
Now let’s download and install the SDK: https://drive.google.com/drive/folders/1Bx7VJiCQvoJd7e8TTtzH-SIujhJSozXF
poddingue@orangepi4-armbian:~$ tar -xvzf /tmp/GTISDK-Linux_aarch64_v4.5.1.0_190823.tgz
poddingue@orangepi4-armbian:~/GTISDK-Linux_aarch64_v4.5.1.0$ sudo -EH pip3 install tqdm
sudo apt install libx11-dev libgtk2.0-dev python-tk
poddingue@orangepi4-armbian:~/GTISDK-Linux_aarch64_v4.5.1.0$ source SourceMe.env Assume running a Debian like Linux distro. Setup environment for running GTI applications on Linux aarch64 5.4.49-rockchip64 GTISDKPATH=/home/poddingue/GTISDK-Linux_aarch64_v4.5.1.0 LD_LIBRARY_PATH=/home/poddingue/GTISDK-Linux_aarch64_v4.5.1.0/Lib/Linux/OpenCV/aarch64:/home/poddingue/GTISDK-Linux_aarch64_v4.5.1.0/Lib/Linux/aarch64 PATH=/home/poddingue/GTISDK-Linux_aarch64_v4.5.1.0/Bin/Linux/aarch64:/home/poddingue/.local/bin:/usr/local/bin:/usr/bin:/bin:/usr/local/games:/usr/games:/home/poddingue/.local/bin Possibly working on an embedded system. Please watch out for missing packages. Check dependency passed diff: /etc/udev/rules.d/50-eusb.rules: No such file or directory EUSB rules are missing or outdated. This is needed if you are using EUSB USB dongles. Do you wish to install? [y/N] Y
opencv
756 sudo apt-get install build-essential cmake pkg-config
poddingue@orangepi4-armbian:~/GTISDK-Linux_aarch64_v4.5.1.0/Apps/Python$ sudo apt install libjpeg62-turbo-dev:armhf libjpeg62-turbo-dev libtiff5-dev
sudo apt-get install libavcodec-dev libavformat-dev libswscale-dev libv4l-dev
$ sudo apt-get install libxvidcore-dev libx264-dev
$ sudo apt-get install libgtk-3-dev
$ sudo apt-get install libatlas-base-dev gfortran
sudo apt-get install python3.7-dev libopenjp2-7-dev ccache libgstreamer1.0-dev
wget https://github.com/opencv/opencv/archive/4.3.0.zip && unzip 4.3.0.zip
wget https://codeload.github.com/opencv/opencv_contrib/zip/4.3.0 && unzip 4.3.0
sudo pip install virtualenv virtualenvwrapper
export WORKON_HOME=$HOME/.virtualenvs
source /usr/local/bin/virtualenvwrapper.sh
in .bashrc
mkvirtualenv cv -p python3
cd opencv-4.3.0/ 796 ll 797 mkdir build 798 cd build
cmake -D CMAKE_BUILD_TYPE=RELEASE -D CMAKE_INSTALL_PREFIX=/usr/local -D INSTALL_PYTHON_EXAMPLES=ON -D INSTALL_C_EXAMPLES=OFF -D OPENCV_EXTRA_MODULES_PATH=~/opencv_contrib-4.3.0/modules -D BUILD_EXAMPLES=ON .. -DPYTHON_DEFAULT_EXECUTABLE=$(which python3)
make
Back to gtilib
sudo apt install python-numpy python-tk
source SourceMe.env
Install Caffe
mkdir build
cd build
cmake ..
Protobuf compiler version doesn't match library version 3.6.1
Okay… Let’s try a sudo apt install protobuf-compiler.
protoc --version
libprotoc 3.6.1
cmake ..
Could NOT find HDF5 (missing: HDF5_LIBRARIES HDF5_INCLUDE_DIRS
My bad, let’s install it.
sudo apt install libhdf5-dev
cmake ..
Could not find a package configuration file provided by "OpenCV" with any
Let’s install openCV, then…
sudo apt install libopencv-dev
cmake ..
[...]
-- Configuring done
-- Generating done
-- Build files have been written to: /home/poddingue/caffe/build
Next step, let’s build it for real. By the way, kiddoes, don’t try this -j6 at home unless you have a good heatsink… Or the machine will stop/hang up/reboot without prior alert.
make all -j6
make pycaffe -j6
make test -j6
make runtest -j6
Run a simple example
Run the caffe example – mnist instance: Mnist is a handwritten digital library. Originally used for handwritten numeral recognition on checks, and it is now the DL’s starting exercise library. The special model for mnist identification is Lenet, which is the earliest CNN model. The training samples of mnist data are 60,000 units, and the test samples are 10,000 units. Each sample is a black and white picture of size 28*28, and the handwritten number is 0-9, so it is divided into 10 categories.
Download the mnist data first
sh data/mnist/get_mnist.sh
cd data/mnist
There are four files in the directory after running the previous command:
ll
total 53676
-rwxr-xr-x 1 poddingue poddingue 408 Jun 22 16:55 get_mnist.sh
-rw-r--r-- 1 poddingue poddingue 7840016 Jul 21 2000 t10k-images-idx3-ubyte # Training set samples
-rw-r--r-- 1 poddingue poddingue 10008 Jul 21 2000 t10k-labels-idx1-ubyte # Corresponding annotation of training set
-rw-r--r-- 1 poddingue poddingue 47040016 Jul 21 2000 train-images-idx3-ubyte # Testing set sample
-rw-r--r-- 1 poddingue poddingue 60008 Jul 21 2000 train-labels-idx1-ubyte # Corresponding annotation of testing set
Converting the data
These data cannot be used directly in Caffe, and need to be converted into LMDB data:
cd ../..
sh examples/mnist/create_mnist.sh
Creating lmdb...
I0622 17\:37\:06.109530 12691 db_lmdb.cpp:35] Opened lmdb examples/mnist/mnist_train_lmdb
I0622 17\:37\:06.114603 12691 convert_mnist_data.cpp:88] A total of 60000 items.
I0622 17\:37\:06.114666 12691 convert_mnist_data.cpp:89] Rows: 28 Cols: 28
I0622 17\:37\:11.407480 12691 convert_mnist_data.cpp:108] Processed 60000 files.
I0622 17\:37\:12.192065 12698 db_lmdb.cpp:35] Opened lmdb examples/mnist/mnist_test_lmdb
I0622 17\:37\:12.194784 12698 convert_mnist_data.cpp:88] A total of 10000 items.
I0622 17\:37\:12.198009 12698 convert_mnist_data.cpp:89] Rows: 28 Cols: 28
I0622 17\:37\:12.566424 12698 convert_mnist_data.cpp:108] Processed 10000 files.
Done.
ll examples/mnist/
total 136
-rw-r--r-- 1 poddingue poddingue 4520 Jun 22 16:55 convert_mnist_data.cpp
-rwxr-xr-x 1 poddingue poddingue 634 Jun 22 16:55 create_mnist.sh
-rw-r--r-- 1 poddingue poddingue 777 Jun 22 16:55 lenet_adadelta_solver.prototxt
-rw-r--r-- 1 poddingue poddingue 778 Jun 22 16:55 lenet_auto_solver.prototxt
-rw-r--r-- 1 poddingue poddingue 6003 Jun 22 16:55 lenet_consolidated_solver.prototxt
-rw-r--r-- 1 poddingue poddingue 871 Jun 22 16:55 lenet_multistep_solver.prototxt
-rw-r--r-- 1 poddingue poddingue 1738 Jun 22 16:55 lenet.prototxt
-rw-r--r-- 1 poddingue poddingue 886 Jun 22 16:55 lenet_solver_adam.prototxt
-rw-r--r-- 1 poddingue poddingue 790 Jun 22 16:55 lenet_solver.prototxt
-rw-r--r-- 1 poddingue poddingue 830 Jun 22 16:55 lenet_solver_rmsprop.prototxt
-rw-r--r-- 1 poddingue poddingue 2282 Jun 22 16:55 lenet_train_test.prototxt
-rw-r--r-- 1 poddingue poddingue 4814 Jun 22 16:55 mnist_autoencoder.prototxt
-rw-r--r-- 1 poddingue poddingue 451 Jun 22 16:55 mnist_autoencoder_solver_adadelta.prototxt
-rw-r--r-- 1 poddingue poddingue 423 Jun 22 16:55 mnist_autoencoder_solver_adagrad.prototxt
-rw-r--r-- 1 poddingue poddingue 466 Jun 22 16:55 mnist_autoencoder_solver_nesterov.prototxt
-rw-r--r-- 1 poddingue poddingue 433 Jun 22 16:55 mnist_autoencoder_solver.prototxt
drwxr--r-- 2 poddingue poddingue 4096 Jun 22 17:37 mnist_test_lmdb
drwxr--r-- 2 poddingue poddingue 4096 Jun 22 17:37 mnist_train_lmdb
-rw-r--r-- 1 poddingue poddingue 11948 Jun 22 16:55 readme.md
-rwxr-xr-x 1 poddingue poddingue 106 Jun 22 16:55 train_lenet_adam.sh
-rwxr-xr-x 1 poddingue poddingue 118 Jun 22 16:55 train_lenet_consolidated.sh
-rwxr-xr-x 1 poddingue poddingue 4517 Jun 22 16:55 train_lenet_docker.sh
-rwxr-xr-x 1 poddingue poddingue 115 Jun 22 16:55 train_lenet_rmsprop.sh
-rwxr-xr-x 1 poddingue poddingue 101 Jun 22 16:55 train_lenet.sh
-rwxr-xr-x 1 poddingue poddingue 120 Jun 22 16:55 train_mnist_autoencoder_adadelta.sh
-rwxr-xr-x 1 poddingue poddingue 119 Jun 22 16:55 train_mnist_autoencoder_adagrad.sh
-rwxr-xr-x 1 poddingue poddingue 120 Jun 22 16:55 train_mnist_autoencoder_nesterov.sh
-rwxr-xr-x 1 poddingue poddingue 117 Jun 22 16:55 train_mnist_autoencoder.sh
The examples/mnist/create_mnist.sh has generated two folders in the examples/mnist/ directory, namely mnist_train_lmdb and mnist_test_lmdb after the LMDB data conversion succeeded. The data.mdb and lock.mdb stored in the folder are the running data we need.
LevelDB Data
If you want to run leveldb data, run the program under examples/siamese/ folder.
./examples/siamese/create_mnist_siamese.sh
Creating leveldb...
Done.
ll examples/siamese/
total 204
-rw-r--r-- 1 poddingue poddingue 4368 Jun 22 16:55 convert_mnist_siamese_data.cpp
-rwxr-xr-x 1 poddingue poddingue 617 Jun 22 16:55 create_mnist_siamese.sh
-rw-r--r-- 1 poddingue poddingue 158921 Jun 22 16:55 mnist_siamese.ipynb
-rw-r--r-- 1 poddingue poddingue 1488 Jun 22 16:55 mnist_siamese.prototxt
-rw-r--r-- 1 poddingue poddingue 810 Jun 22 16:55 mnist_siamese_solver.prototxt
drwxr-xr-x 2 poddingue poddingue 4096 Jun 22 17:39 mnist_siamese_test_leveldb
drwxr-xr-x 2 poddingue poddingue 4096 Jun 22 17:39 mnist_siamese_train_leveldb
-rw-r--r-- 1 poddingue poddingue 4907 Jun 22 16:55 mnist_siamese_train_test.prototxt
-rw-r--r-- 1 poddingue poddingue 5949 Jun 22 16:55 readme.md
-rwxr-xr-x 1 poddingue poddingue 125 Jun 22 16:55 train_mnist_siamese.sh
Next modify the configuration file lenet_solver.prototxt
vi ./examples/mnist/lenet_solver.prototxt
As needed, set the maximum number of iterations at 100 and the last line, solver_mode, to CPU:
# The train/test net protocol buffer definition
net: "examples/mnist/lenet_train_test.prototxt"
# test_iter specifies how many forward passes the test should carry out.
# In the case of MNIST, we have test batch size 100 and 100 test iterations,
# covering the full 10,000 testing images.
test_iter: 100
# Carry out testing every 500 training iterations.
test_interval: 500
# The base learning rate, momentum and the weight decay of the network.
base_lr: 0.01
momentum: 0.9
weight_decay: 0.0005
# The learning rate policy
lr_policy: "inv"
gamma: 0.0001
power: 0.75
# Display every 100 iterations
display: 100
# The maximum number of iterations
max_iter: 10000
# snapshot intermediate results
snapshot: 5000
snapshot_prefix: "examples/mnist/lenet"
# solver mode: CPU or GPU
solver_mode: CPU
Finally, run this example:
root@OrangePi:~/caffe# time sh examples/mnist/train_lenet.sh I0110 06:28:06.117972 25078 caffe.cpp:197] Use CPU. I0110 06:28:06.118988 25078 solver.cpp:45] Initializing solver from parameters: test_iter: 100 test_interval: 500 base_lr: 0.01 display: 100 XUNLONG Software Co,. Ltd All rights reserved 36 www.orangepi.com max_iter: 10000 lr_policy: “inv” gamma: 0.0001 power: 0.75 momentum: 0.9 weight_decay: 0.0005 snapshot: 5000 snapshot_prefix: “examples/mnist/lenet” solver_mode: CPU net: “examples/mnist/lenet_train_test.prototxt” …… …… …… I0110 07:25:37.016746 25078 sgd_solver.cpp:284] Snapshotting solver state to binary proto file examples/mnist/lenet_iter_10000.solverstate I0110 07:25:37.146054 25078 solver.cpp:327] Iteration 10000, loss = 0.00200602 I0110 07:25:37.146195 25078 solver.cpp:347] Iteration 10000, Testing net (#0) I0110 07:25:54.299634 25080 data_layer.cpp:73] Restarting data prefetching from start. I0110 07:25:55.010598 25078 solver.cpp:414] Test net output #0: accuracy = 0.9913 I0110 07:25:55.010757 25078 solver.cpp:414] Test net output #1: loss = 0.0273203 (* 1 = 0.0273203 loss) I0110 07:25:55.010777 25078 solver.cpp:332] Optimization Done. I0110 07:25:55.010793 25078 caffe.cpp:250] Optimization Done. real 57m48.984s user 58m6.479s sys 0m1.977s ⑦Operation conclusion According to the above results, the running time of the CPU is about 58 minutes, with an accuracy of about 99%.