When working on build predictive application using machine learning algorithms, you will probably be working with such languages as Python, R, PyTorch, TensorFlow, and lots of other frameworks. One of the challenges we face is taking these machine learning models from our test/lab environment and putting into production them. By this I mean integrating them with our production systems to allow real-time use of these ML models. This is not a topic that is discussed very often. Many of the most common languages and frameworks are very easy to use for machine learning, but running them in production can be slow. This can lead to lots of problems and can regularly label machine learning projects as a failure. None of use want that. Sometime people look are re-coding all the machine learning models in other languages such as C or Java or Julia, as these are noted for the high speed and scalability in production environments. (Remember many of the common ML languages and frameworks are actually developed using C and Java.)
To remove the need to recode your models, many of the languages, frameworks and tools have opened to the ability to allow model interchange. This approach allows you to use the tools that work best for you, in your environment and your company, to develop, test and evaluate machine learning models. These can then be packaged up and shared with other languages, frameworks or tools suitable for production environments, eliminating or significantly reducing the need for large coding projects and allows for quicker time to deployment.
There are many machine learning model interchange frameworks available. Historically PMML was popular but with the rise of other machine learning and deep learning algorithms, it seems to have lost the popularity contest. One of the more popular machine learning interchange frameworks is called ONNX. This has been growing in popularity with a wide body of languages, tools and vendors.
ONNX stands for the Open Neural Network eXchange and is designed to allow developers to easily move between different machine learning and deep learning frameworks. This allows the easy migration from research and model development environments, to other environments more suited to deployment, allowing for faster scoring of data. ONNX allows for the migration of the model with the minimum of recoding. ONNX generates or provides for an extensible computation dataflow graph model, with built-in operators and data types focused on interencing.
To use ONNX with Python install the library:
pip3 install onnx-mxnet
The following is an extract of sample code generating a model, converting it to ONNX format and saving it to file.
#train a model #load sklearn from sklearn.datasets import load_iris from sklearn.model_selection import train_test_split from sklearn.ensemble import RandomForestClassifier #load the IRIS sample data set iris = load_iris() X, y = iris.data, iris.target #create the train and test data sets X_train, X_test, y_train, y_test = train_test_split(X, y) #define and create Random Forest data set rf = RandomForestClassifier() rf.fit(X_train, y_train) #convert into ONNX format & save to file from skl2onnx import convert_sklearn from skl2onnx.common.data_types import FloatTensorType initial_type = [('float_input', FloatTensorType([None, 4]))] #covert to ONNX onx = convert_sklearn(rf, initial_types=initial_type) #save to file with open("rf_iris.onnx", "wb") as f: f.write(onx.SerializeToString())
The above example illustrates converting a sklearn model. For algorithms and models, converters exist and are available in the ONNX Github
You: What? You can’t be serious? Machine Learning on Mobile Devices?
Me: The simple answer is ‘Yes you can!”
You: But, what about all the complex data processing, CPU or GPU, and everything else that is needed for machine learning?
Me: Yes you are correct, those things might not be needed. What’s the answer to everything in IT?
You: It Depends ?
Me: Exactly. Yes It Depends on what you are doing. In most cases you don’t need large amounts of machine processing power to do machine learning. Except if you are doing image processing. Then you do need a bit of power to support that work.
You: But how can a mobile device be used for machine learning?
Me: It Depends! 🙂 It depends on what you are doing. Most of the data processing power needed is for creating the models. That is what most people talk about. Very few people talk about the deployment of machine learning. Deployment, as in, using the machine learning models in your applications.
You: But why mobile devices? That sounds a bit silly?
Me: It does a bit. But when you think about it, how much do you use your mobile phone and tablet? Where else have you seen mobile devices being used?
You: I use these all the time, to do nearly everything. Just like everyone else I know.
Me: Exactly! and where else have you seen mobile devices being used?
You: Everywhere! hotels, bars, shops, hospitals, everywhere!
Me: Exactly. And it kind of makes sense to have machine learning scoring done at the point of capture of the data and not some hours or days or weeks later in some data warehouse or something else.
You: But what about the processing power of these devices. They aren’t powerful enough to run the machine learning models? Or are they?
Me: What is a machine learning model? In a simple way it is a mathematical formula of the data that calculates a particular outcome. Something that is a bit more complicated than using a sum function. Could a mobile device do that easily?
You: Yes. That should be really easy and fast for mobile devices? But machine learning is complex. People keep telling me how complex it is and how difficult it is!
Me: True it can be, but for most problems it can be as simple as writing a few lines of code to create a model. 3-4 lines of code in some languages. But the applying of the the machine learning model can be a simple task (maybe 1 line of code), although some simple data formatting might be needed, but that is a simple task too.
You: So, how can a machine learning model be run on a mobile device?
Me: Programmers write code to run applications on mobile devices. This code can be extended to include the machine learning model. This can be used to score or label the data or do some other processing. A few lines of code. A good alternative is to create a web service to all the remove scoring of the data.
You: The programming languages used for mobile development are a bit different to most other applications. Surely those mobile device languages don’t support machine learning.
Me: You’d be surprised by what’s available.
You: OK, What languages can I try? Where can I get started?
You. Brilliant, thank you Brendan. I’ll let you know how I get on with those.
In a previous blog post I gave some examples of how facial images recognition and videos are being used in our daily lives. In this post I want to extend this with some additional examples. There are ethical issues around this and in some of these examples their usage has stopped. What is also interesting is the reaction on various social media channels about this. People don’t like it and and happen that some of these have stopped.
But how widespread is this technology? Based on these known examples, and this list is by no means anywhere near complete, but gives an indication of the degree of it’s deployment and how widespread it is.
Dubai is using facial recognition to measure customer satisfaction at four of the Roads and Transport Authority Customer Happiness Centers. They analyze the faces of their customers and rank their level of happiness. They can use this to generate alerts when the happiness levels falls below certain levels.
Various department stores are using facial recognition throughout the stores and at checkout. These are being used to delivery personalized adverts to users on either in-store screen or on personalized screens on the shopping trolley. And can be used to verify a person’s age if they are buying alcohol or other products. Tesco’s have previously used face-scanning cameras at tills in petrol stations to target advertisements at customers depending on their age and approximate age.
Some retail stores are using ML to monitor you, monitor what items you pick up and what you pay for at the checkout, identifying any differences and what steps to take next.
In a slight variation of facial recognition, some stores are using similar technology to monitor stock levels, monitor how people interact with different products (e.g pick up one product and then relate it with a similar product), and optimized location of products. Walmart has been a learner in the are of AI and Machine Learning in the retail section for some time now.
The New York Metropolitan Transport Authority has been using facial capture and recognition at several site across the city. Their proof of concept location was at the Robert F Kennedy Bridge. The company supplying the technology claimed 80% accuracy at predicting the person, through a widescreen while the car was traveling at low speed. These images can then be matched against government databases, such as driver license authorities, police databases and terrorist databases. The problem with this project was that it did not achieve one single positive match (within acceptable parameters) during the initial period of the project.
There are some reports that similar technology is being use on the New York Subway system in Time Square to help with identifying fare dodgers.
How about using facial recognition at boarding gates for your new flight instead of showing your passport or other official photo id. JetBlue and other airlines are now using this technology. Some airports have been using this for many many years.
San Francisco City government took steps in May 2019 to ban the use of facial recognition across all city functions. Other cities like Oakland and Sommerville in Massachusetts have implemented similar bans with other cities likely to follow. But it doesn’t ban the use by private companies.
What about using this technology to automatically monitor and manage staff. Manage staff, as in to decide who should be fired and who should be reallocated elsewhere. It is reported that Amazon is using facial and other recognition systems to monitor staff productivity in their warehouses.
A point I highlighted in my previous post was how are these systems/applications able to get enough images as training samples for their models. This is considering that most of the able systems/applications say they don’t keep any of the images they capture.
How many of us take pictures and post them on Facebook, Instagram, Snapchat, Twitter, etc. By doing this, you are making those images available to these companies to training their machine learning model. To do this they scrap the images for these sites and then have to manually label them with descriptive information. It is a combination of the image and descriptive information that is used by the machine learning algorithms to learn and build a model that suits their needs. See the MIT Technology Review article for more details and example on this topic.
There are also reports of some mobile phone apps that turn on your mobile phone camera. The apps will detect if the phone is possibly mounted on the dashboard of a car, and then takes pictures of the inside of the car and also pictures of where you are driving. Similar reports exists about many apps and voice activated devices.
So be careful what you post on social media or anywhere else online, and be careful of what apps you have on your mobile phone!
There is a general backlash to the use of this technology, and with more people becoming aware of what is happening, we need to more aware of what when and where this technology is being used.
Over the past 18 months or so most of the examples of using machine learning have been on looking at images and identifying objects in them. There are the typical examples of examining pictures looking for a Cat or a Dog, or some famous person, etc. Most of these examples are very noddy, although they do illustrate important examples.
But what if this same technology was used to monitor people going about their daily lives. What if pictures and/or video was captured of you as you walked down the street or on your way to work or to a meeting. These pictures and videos are being taken of you without you knowing.
And this raises a wide range of Ethical concerns. There are the ethics of deploying such solutions in the public domain, but there are also ethical concerns for the data scientists, machine learner, and other people working on these projects. “Just because we can, doesn’t mean we should”. People need to decide, if they are working on one of these projects, if they should be working on it and if not what they can do.
Ethics are the principals of behavior based on ideas of right and wrong. Ethical principles often focus on ideas such as fairness, respect, responsibility, integrity, quality, transparency and trust. There is a lot in that statement on Ethics, but we all need to consider that is right and what is wrong. But instead of wrong, what is grey-ish, borderline scenarios.
Here are some examples that might fall into the grey-ish space between right and wrong. Why they might fall more towards the wrong is because most people are not aware their image is being captured and used, not just for a particular purpose at capture time, but longer term to allow for better machine learning models to be built.
Can you imagine walking down the street with a digital display in front of you. That display is monitoring you, and others, and then presents personalized adverts on the digital display aim specifically at you. A classify example of this is in the film Minority Report. This is no longer science fiction.
This is happening at the Westfield shopping center in London and in other cities across UK and Europe. These digital advertisement screens are monitoring people, identifying their personal characteristics and then customizing the adverts to match in with the profile of the people walking past. This solutions has been developed and rolled out by Ocean Out Door. They are using machine learning to profile the individual people based on gender, age, facial hair, eye wear, mood, engagement, attention time, group size, etc. They then use this information to:
- Optimisation – delivering the appropriate creative to the right audience at the right time.
- Visualise – Gaze recognition to trigger creative or an interactive experience
- AR Enabled – Using the HD cameras to create an augmented reality mirror or window effect, creating deep consumer engagement via the latest technology
- Analytics – Understanding your brand’s audience, post campaign analysis and creative testing
Face Plus Plus can monitor people walking down the street and do similar profiling, and can bring it to another level where by they can identify what clothing you are wearing and what the brand is. Image if you combine this with location based services. An example of this, imagine you are walking down the high street or a major retail district. People approach you trying to entice you into going into a particular store, and they offer certain discounts. But you are with a friend and the store is not interested in them.
The store is using video monitoring, capturing details of every person walking down the street and are about to pass the store. The video is using machine/deep learning to analyze you profile and what brands you are wearing. The store as a team of people who are deployed to stop and engage with certain individuals, just because they make the brands or interests of the store and depending on what brands you are wearing can offer customized discounts and offers to you.
How comfortable would you be with this? How comfortable would you be about going shopping now?
For me, I would not like this at all, but I can understand why store and retail outlets are interested, as they are all working in a very competitive market trying to maximize every dollar or euro they can get.
Along side the ethical concerns, we also have some legal aspects to consider. Some of these are a bit in the grey-ish area, as some aspects of these kind of scenarios are slightly addresses by EU GDPR and the EU Artificial Intelligence guidelines. But what about other countries around the World. Then it comes to training and deploying these facial models, they are dependent on having a good training data set. This means they needs lots and lots of pictures of people and these pictures need to be labelled with descriptive information about the person. For these public deployments of facial recognition systems, then will need more and more training samples/pictures. This will allow the models to improve and evolve over time. But how will these applications get these new pictures? They claim they don’t keep any of the images of people. They only take the picture, use the model on it, and then perform some action. They claim they do not keep the images! But how can they improve and evolve their solution?
I’ll have another blog post giving more examples of how machine/deep learning, video and image captures are being used to monitor people going about their daily lives.