EFM Series: Using MiNiFi Agents on Raspberry Pi 4 with Intel Movidius Neural Compute Stick 2, Apache NiFi and AI

EFM Series:   Using MiNiFi Agents on Raspberry Pi 4 with Intel Movidius Neural Compute Stick 2, Apache NiFi and AI

The good news is Raspberry Pi 4 can run MiNiFi Java Agents, Intel Movidius Neural Compute Stick 2 and AI libraries.   You can now use this 4GB of RAM device to run IoT with AI on the edge.

Flow From MiNiFi Agent Running OpenVino, SysLog Tail and Grabbing WebCam Images

Configure The Execution of OpenVino Python Applications on RPI 4

Events Returning from Raspberry Pi 4

Models Used

Download model using downloader.

Github

https://github.com/tspannhw/minifi-rpi4-ncc2

DATE=$(date +"%Y-%m-%d_%H%M")
fswebcam -q -r 1280x720 --no-banner /opt/demo/images/$DATE.jpg

python3 /opt/intel/openvino/build/test.py /opt/demo/images/$DATE.jpg

Software

• Apache NiFi
• Apache NiFi - MiNiFi Agents
• TensorFlow
• OpenVino
• Python 3
• FSWEBCAM
• OpenCV DNN
• PSUTIL

Python Libraries

pip3 install getmac

pip3 install psutil

pip3 install --upgrade pip
pip3 install --upgrade setuptools

• Intel Movidius Neural Compute Stick 2
• Raspberry Pi 4 with 4GB RAM

Hosting

We can run On-Premise on VMs, Containers, K8 or Bare metal.   Or on own of the clouds such as Google.

Resources

• https://github.com/movidius/ncappzoo
• https://docs.openvinotoolkit.org/latest/_docs_install_guides_installing_openvino_raspbian.html
• https://github.com/movidius/ncappzoo/blob/master/tensorflow/README.md
• https://software.intel.com/en-us/articles/python3-sbc-and-ncs2
• https://github.com/opencv/open_model_zoo
• https://download.01.org/opencv/2019/open_model_zoo/R2/20190628_180000_models_bin/
• https://docs.openvinotoolkit.org/latest/_intel_models_index.html
• https://docs.openvinotoolkit.org/latest/_intel_models_person_detection_retail_0013_description_person_detection_retail_0013.html
• https://docs.openvinotoolkit.org/latest/_intel_models_person_detection_action_recognition_0006_description_person_detection_action_recognition_0006.html
• https://docs.openvinotoolkit.org/latest/_intel_models_pedestrian_and_vehicle_detector_adas_0001_description_pedestrian_and_vehicle_detector_adas_0001.html
• https://github.com/opencv/open_model_zoo/blob/master/tools/downloader/README.md
• https://github.com/opencv/open_model_zoo/blob/master/demos/README.md
• https://github.com/opencv/open_model_zoo/blob/master/demos/gaze_estimation_demo/README.md
• https://github.com/opencv/open_model_zoo/blob/master/demos/security_barrier_camera_demo/README.md
• https://github.com/opencv/open_model_zoo/blob/master/demos/pedestrian_tracker_demo/README.md
• https://github.com/opencv/open_model_zoo/blob/master/demos/text_detection_demo/README.md
• https://github.com/movidius/ncappzoo/tree/master/apps/simple_classifier_py
• https://download.01.org/openvinotoolkit/2018_R5/open_model_zoo/text-detection-0001/FP32/
• http://docs.openvinotoolkit.org/latest/_inference_engine_samples_object_detection_sample_ssd_README.html
• https://software.intel.com/en-us/articles/get-started-with-neural-compute-stick
• https://apps.apple.com/us/app/pihelper/id1369930932

Directories

•  /root/inference_engine_samples_build/armv7l/Release
• /opt/intel/openvino

Barcelona DataWorks Summit March 2019

I just returned from this awesome event.   Not even a rough plane trip can damper my spirits after seeing all the amazing things and all that we got to do this year.   It was nice to see familiar faces from attendees from 2017 and 2018 including my friends from Prague and Germany!

Thanks to Andy LoPresto, George Vetticaden, Dinesh Chandrasekhar, Purnima, Nathan, Dan Chaffelson for great pictures, talks, support and being an amazing team for Data in Motionists.

Meetup

The meetup was great and in the same hall as some other amazing meetups at the same time. A great experience for those at Summit early (and open to all people for free).

https://www.slideshare.net/bunkertor/the-edge-to-ai-deep-dive-barcelona-meetup-march-2019

https://www.meetup.com/futureofdata-barcelona/events/259345951/

Highlight:  Dan spinning up NiFi at scale in the audience on Google Cloud on K8 with ease!

Highlight:  Andy’s crushing it MiNiFi and NiFi presentation! I think he has too many RPIs!

Demopalooza

Edge to AI

https://dataworkssummit.com/barcelona-2019/session/edge-to-ai-analytics-from-edge-to-cloud-with-efficient-movement-of-machine-data/

https://www.slideshare.net/bunkertor/edge-to-ai-analytics-from-edge-to-cloud-with-efficient-movement-of-machine-data

Apache Deep Learning 201

https://dataworkssummit.com/barcelona-2019/session/apache-deep-learning-201/

https://www.slideshare.net/bunkertor/apache-deep-learning-201-barcelona-dws-march-2019

All the Githubs

https://github.com/tspannhw/DWS2019Barcelona?_lrsc=c48b47b6-6b54-466a-87f6-457457dd21ec

All the great Apache NiFi content from Andy LoPresto is here including custom processors:
https://github.com/alopresto/slides/blob/master/dws_barcelona_2019/
https://github.com/alopresto/slides

Using Raspberry Pi 3B+ with Apache NiFi MiNiFi and Google Coral Accelerator and Pimoroni Inky Phat

Using Raspberry Pi 3B+ with Apache NiFi MiNiFi and Google Coral Accelerator and Pimoroni Inky Phat

Architecture

Introduction

First we need to unbox our new goodies.   The Inky Phat is an awesome E-Ink display with low power usage that stays displayed after shutdown! 

Next I added a new Google Coral Edge TPU ML Accelerator USB Coprocessor to a new Raspberry Pi 3B+.    This was so easy to integrate and get up and running.

Let's unbox this beautiful device (but be careful when it runs it can get really hot and there is a warning in the instructions).   So I run this on top of an aluminum case and with a big fan on it.

Pimoroni Inky Phat

It is pretty easy to set this up and it provides a robust Python library to write to our E-Ink display.   You can see an example screen here.

https://github.com/pimoroni/inky
Pimoroni Inky pHAT ePaper eInk Display in Red

Pimoroni Inky Phat (Red)

https://shop.pimoroni.com/products/inky-phat
https://github.com/pimoroni/inky
https://pillow.readthedocs.io/en/stable/reference/ImageDraw.html
https://learn.pimoroni.com/tutorial/sandyj/getting-started-with-inky-phat


Install Some Python Libraries and Debian Install for Inky PHAT and Coral

pip3 install font_fredoka_one
pip3 install geocoder
pip3 install fswebcam
sudo apt-get install fe
pip3 install psutil
pip3 install font_hanken_grotesk
pip3 install font_intuitive
wget http://storage.googleapis.com/cloud-iot-edge-pretrained-models/edgetpu_api.tar.gz

These libraries are for the Inky, it needs fonts to write.   The last TAR is for the Edge device and is a fast install documented well by Google.

Download Apache NiFi - MiNiFi Java Agent

https://nifi.apache.org/minifi/download.html

Next up, the most important piece.  You will need to have JDK 8 installed on your device if you are using the Java agent.   You can also use the MiniFi C++ Agent but that may require building it for your OS/Platform.   That has some interesting Python running abilities.

Google Coral Documentation - Google Edge TPU

• Google Edge TPU ML accelerator coprocessor
• USB 3.0 Type-C socket
• Supports Debian Linux on host CPU
• ASIC designed by Google that provides high performance ML inferencing for TensorFlow Lite models

• https://coral.withgoogle.com/tutorials/edgetpu-retrain-classification-ondevice/
• https://coral.withgoogle.com/tutorials/edgetpu-api/
• http://storage.googleapis.com/cloud-iot-edge-pretrained-models/edgetpu_api_reference.zip
• https://coral.withgoogle.com/web-compiler/
• https://coral.withgoogle.com/tutorials/edgetpu-models-intro/
• https://coral.withgoogle.com/tutorials/accelerator/
• https://coral.withgoogle.com/tutorials/edgetpu-api/
• https://coral.withgoogle.com/models/
• https://coral.withgoogle.com/tutorials/accelerator-datasheet/

Using Pretrained Tensorflow Lite Model:

Inception V4 (ImageNet)
Recognizes 1,000 types of objects
Dataset: ImageNet
Input size: 299x299

Let's run a flow!

I can run this Python3 script every 10 seconds without issues that includes capturing the picture, running it through classification with the model, forming JSON data, grabbing network and device stats, forming a JSON file and completing in under 5 seconds.   Our MiNiFi agent is scheduled to call the script every 10 seconds and grab images after 60 seconds. 


MiNiFi Flow

Flow Overview

Apache NiFi Flow

Results (Once an hour we update our E-Ink Display with Date, IP, Run Time, Label 1)

Example JSON Data

{"endtime": "1552164369.27", "memory": "19.1", "cputemp": "32", "ipaddress": "192.168.1.183", "diskusage": "50336.5", "score_2": "0.14", "score_1": "0.68", "runtime": "4.74", "host": "mv2", "starttime": "03/09/2019 15:46:04", "label_1": "hard disc, hard disk, fixed disk", "uuid": "20190309204609_05c9a240-d801-4bac-b029-e5bf38c02d40", "label_2": "buckle", "systemtime": "03/09/2019 15:46:09"}

Example Slack Alert

PS3 Eye USB Camera Capturing an Image

Image It Captured

Source Code

https://github.com/tspannhw/nifi-minifi-coral

Convert Your Flow To Config.YML For MiniFi (Look for a major innovation here soon).

 ./config.sh transform Coral_MiniFi_Agent_Flow.xml config.yml

config.sh: JAVA_HOME not set; results may vary

Java home: 

MiNiFi Toolkit home: /Volumes/TSPANN/2019/apps/minifi-toolkit-0.5.0

No validation errors found in converted configuration.

Example Call From MiNiFi 0.5.0 Java Agent to Apache NiFi 1.9.0 Server

2019-03-09 16:21:01,877 INFO [Timer-Driven Process Thread-10] o.a.nifi.remote.StandardRemoteGroupPort RemoteGroupPort[name=Coral Input,targets=http://hw13125.local:8080/nifi] Successfully sent [StandardFlowFileRecord[uuid=eab17784-2e76-4438-a60a-fd67df37a102,claim=StandardContentClaim [resourceClaim=StandardResourceClaim[id=1552166446123-3, container=default, section=3], offset=362347, length=685083],offset=0,name=d74bc911bfd167fe79d5a3aa780004fd66fa6d,size=685083], StandardFlowFileRecord[uuid=eb979d09-a936-4b2d-82ff-d204f9d768eb,claim=StandardContentClaim [resourceClaim=StandardResourceClaim[id=1552166446123-3, container=default, section=3], offset=1047430, length=361022],offset=0,name=2019-03-09_1541.jpg,size=361022], StandardFlowFileRecord[uuid=343a4c91-b863-440e-ac81-1f68d6210792,claim=StandardContentClaim [resourceClaim=StandardResourceClaim[id=1552166446123-3, container=default, section=3], offset=1408452, length=668],offset=0,name=3026822c780724b39e826230bdef43f8ed9786,size=668], StandardFlowFileRecord[uuid=97df9d3a-dc3c-4d03-b533-7b75c3180032,claim=StandardContentClaim [resourceClaim=StandardResourceClaim[id=1552166446123-3, container=default, section=3], offset=1409120, length=2133417],offset=0,name=abb6feaac5bda3c6d3660e7593cc4ef2e1cfce,size=2133417]] (3.03 MB) to http://hw13125.local:8080/nifi-api in 1416 milliseconds at a rate of 2.14 MB/sec

References

• https://medium.freecodecamp.org/building-an-iiot-system-using-apache-nifi-mqtt-and-raspberry-pi-ce1d6ed565bc
• https://community.hortonworks.com/articles/85984/using-minifi-to-read-data-from-a-sense-hat-on-a-ra.html
• https://community.hortonworks.com/articles/107379/minifi-for-image-capture-and-ingestion-from-raspbe.html
• https://community.hortonworks.com/articles/107379/minifi-for-image-capture-and-ingestion-from-raspbe.html
• https://community.hortonworks.com/articles/32605/running-nifi-on-raspberry-pi-best-practices.html
• https://www.tensorflow.org/lite/convert/cmdline_examples
• https://www.tensorflow.org/lite/guide/get_started
• https://pillow.readthedocs.io/en/stable/reference/ImageDraw.html
• https://coral.withgoogle.com/tutorials/edgetpu-faq/ 

Apache NiFi + Deep Speech

Deep Speech with Apache NiFi 1.8

Tools: Python 3.6, PyAudio, TensorFlow, Deep Speech, Shell, Apache NiFi

Why: Speech-to-Text

Use Case: Voice control and recognition.

Series: Holiday Use Case: Turn on Holiday Lights and Music on command.

Cool Factor: Ever want to run a query on Live Ingested Voice Commands?

Other Options: https://community.hortonworks.com/articles/155519/voice-controlled-data-flows-with-google-aiy-voice.html

We are using Python 3.6 to write some code around pyaudio, tensorflow and Deep Speech to capture audio, store it in a wave file and then process it with Deep Speech to extract some text. This example is running in OSX without a GPU on Tensorflow v1.11.

The Mozilla Github repo for their Deep Speech implementation has nice getting started information that I used to integrate our flow with Apache NiFi.

Installation as per https://github.com/mozilla/DeepSpeech

pip3 install deepspeech
wget -O - https://github.com/mozilla/DeepSpeech/releases/download/v0.3.0/deepspeech-0.3.0-models.tar.gz | tar xvfz -

This pre-trained model is available for English. For other languages, you will need to build your own. You can use a beef HDP 3.1 cluster to train this. Note: THIS IS A 1.8 GIG DOWNLOAD. That may be an issue for laptops, devices or small data people.

Apache NiFi Flow

The flow is simple, we call our shell script that runs Python that records audio and sends it to Deep Speech for processing.

We get back a voice_string in JSON that we turn into a record for querying and filtering in Apache NiFi.

I am handling a few voice commands for "Save", "Load" and "Move". As you can imagine you can handle pretty much anything you want. It's a simple way to use voice to control streaming data flows or just to ingest large streams of text. Even using advanced Deep Learning, text recognition is still not the strongest.

If you are going to load balance connections between nodes, you have options on compression and load balancing strategies. This can come in handy if you have a lot of servers.

Shell Script

python3.6 /Volumes/TSPANN/projects/DeepSpeech/processnifi.py /Volumes/TSPANN/projects/DeepSpeech/models/output_graph.pbmm /Volumes/TSPANN/projects/DeepSpeech/models/alphabet.txt

Schema

{
  "type" : "record",
  "name" : "voice",
  "fields" : [ {
    "name" : "systemtime",
    "type" : "string",
    "doc" : "Type inferred from '\"12/10/2018 14:53:47\"'"
  }, {
    "name" : "voice_string",
    "type" : "string",
    "doc" : "Type inferred from '\"\"'"
  } ]
}

We can add more fields as needed.

Example Run

HW13125:DeepSpeech tspann$ ./runnifi.sh
TensorFlow: v1.11.0-9-g97d851f04e
DeepSpeech: unknown
2018-12-10 14:36:43.714433: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
{"systemtime": "12/10/2018 14:36:43", "voice_string": "one two three or five six seven eight nine"}

We can run this on top of YARN 3.1 as dockerized or non-dockerized workloads.

Setting up nodes to run HDF 3.3 - Apache NiFi and friends is easy in the cloud or on-premise in OpenStack with super devops tools.

When running Apache NiFi it is easy to monitor in Ambari:

References:

• https://github.com/mozilla/DeepSpeech
• https://community.hortonworks.com/articles/224268/running-tensorflow-on-yarn-31-with-or-without-gpu.html
• https://arxiv.org/abs/1412.5567
• https://github.com/tspannhw/nifi-deepspeech