This guide will take you through installing the requirements for the OneAPI Acute Lymphoblastic Leukemia Classifier.
Before you can install this project, there are some prerequisites.
For this project you will need a functioning HIAS Server. To install the HIAS Server, follow the HIAS Server Installation Guide
For this project you will use the model created in the CNN project. If you would like to train your own model you can follow the CNN guide, or you can use the pre-trained model and weights provided in the Model directory.
If you are training the model yourself, you need to convert your model to an Intermediate Representation so that it can be used with OpenVINO and the Neural Compute Stick 2.
To do this, once you have finished the OneAPI Acute Lymphoblastic Leukemia Classifier CNN tutorial, use the following commands, replacing PathToProject with the path to the CNN project:
cd C:\Program Files (x86)\IntelSWTools\openvino\bin\
setupvars.bat
cd C:\Program Files (x86)\IntelSWTools\openvino\deployment_tools\model_optimizer
python3 mo_tf.py --input_model PathToProject\Model\Freezing\frozen.pb --input_shape [1,100,100,3] --output_dir PathToProject\Model\IR --reverse_input_channels --generate_deprecated_IR_V7
The Intermediate Representation for your model will now be accessible in the CNN project IR directory, you need to copy these files to your Raspberry Pi in the same location in the RPI4 Model directory.
For this Project, the operating system choice is Raspberry Pi Buster, previously known as Raspian.
To install Intel® Distribution of OpenVINO™ Toolkit for Raspberry Pi, navigate to the home directory on your Raspberry Pi and use the following commands:
wget https://download.01.org/opencv/2020/openvinotoolkit/2020.4/l_openvino_toolkit_runtime_raspbian_p_2020.4.287.tgz
sudo mkdir -p /opt/intel/openvino
sudo tar -xf l_openvino_toolkit_runtime_raspbian_p_2020.4.287.tgz --strip 1 -C /opt/intel/openvino
sudo apt install cmake
source /opt/intel/openvino/bin/setupvars.sh
echo "source /opt/intel/openvino/bin/setupvars.sh" >> ~/.bashrc
Now we will set up ready for Neural Compute Stick 2.
sudo usermod -a -G users "$(whoami)"
Now close your existing terminal and open a new open. Once in your new terminal use the following commands:
sh /opt/intel/openvino/install_dependencies/install_NCS_udev_rules.sh
You will need a HIAS iotJumpWay device to run this application. Log in to your HIAS Server UI and navigate to IoT->Devices and click on the + button to create a new device.
Fill in the details and once you click Create you will be provided with the credentials for your iotJumpWay device. Make sure you save the Blockchain password as you will not be able to recover or change them in the future, the other credenitials you will be able to retrieve through the device page and/or reset them.
Open the configuration file config.json and fill in your HIAS iotJumpWay and HIAS iotJumpWay device details.
"iotJumpWay": {
"host": "",
"port": 8883,
"ip": "localhost",
"ipinfo": "",
"lid": 0,
"zid": 0,
"did": 0,
"dn": "",
"un": "",
"pw": ""
}
Clone the OneAPI Acute Lymphoblastic Leukemia Classifier repository from the Peter Moss Acute Myeloid & Lymphoblastic Leukemia AI Research Project Github Organization.
To clone the repository and install the OneAPI Acute Lymphoblastic Leukemia Classifier Classifier, make sure you have Git installed. Now navigate to the a directory on your device using commandline, and then use the following command.
git clone https://github.com/AMLResearchProject/oneAPI-ALL-Classifier.git
Once you have used the command above you will see a directory called oneAPI-ALL-Classifier in your home directory.
ls
Using the ls command in your home directory should show you the following.
oneAPI-ALL-Classifier
Navigate to oneAPI-ALL-Classifier/RPI4 directory, this is your project root directory for this tutorial.
Developers from the Github community that would like to contribute to the development of this project should first create a fork, and clone that repository. For detailed information please view the CONTRIBUTING guide. You should pull the latest code from the development branch.
git clone -b "0.5.0" https://github.com/AMLResearchProject/oneAPI-ALL-Classifier.git
The -b "0.5.0" parameter ensures you get the code from the latest master branch. Before using the below command please check our latest master branch in the button at the top of the project README.
All other requirements are included in Setup.sh. You can run this file on machine by navigating to the RPI4 directory in terminal and using the commands below:
sed -i 's/\r//' Setup.sh
sh Setup.sh
Now you can continue with the OneAPI OpenVINO Raspberry Pi 4 Acute Lymphoblastic Leukemia Classifier tutorial
The Peter Moss Acute Myeloid & Lymphoblastic Leukemia AI Research project encourages and youlcomes code contributions, bug fixes and enhancements from the Github.
Please read the CONTRIBUTING document for a full guide to forking our repositories and submitting your pull requests. You will also find information about our code of conduct on this page.
- Adam Milton-Barker - Asociacion De Investigacion En Inteligencia Artificial Para La Leucemia Peter Moss President/Lead Developer, Sabadell, Spain
You use SemVer for versioning. For the versions available, see Releases.
This project is licensed under the MIT License - see the LICENSE file for details.
You use the repo issues to track bugs and general requests related to using this project. See CONTRIBUTING for more info on how to submit bugs, feature requests and proposals.