Selecting ‘special’ photos on your phone

At the beginning of the new year I always want to clean up my photos on my phone. It just never happens.

So now (like so many others I think) I have a lot of photos on my phone from the last 3.5 years. The iPhone photos app helps you a bit to go through your photos. But which ones are really special and you definitely want to keep?

Well, just apply some machine learning.

  1. I run all my photos through a VGG16 deep learning model to generate high dimensional features per photo (on my laptop without GPU this takes about 15 minutes for 2000 photos).
  2. The dimension is 25.088, which is difficult to visualize. I apply a UMAP dimension reduction to bring it back to 3.
  3. In R you can create an interactive 3D plot with plotly where each point corresponds to a photo. Using crosstalk, you can link it to the corresponding image. The photo appears when you hover over the point.

Well a “special” outlying picture in the scatter plot are my two children with a dog during a holiday a few years ago. I had never found it that fast. There are some other notable things that I can see, but I won’t bother you with it here ūüôā

Link GitHub repo with to two R scripts to cluster your own photos. Cheers, Longhow

Advertisements

An R Shiny app to recognize flower species

Introduction

Playing around with PyTorch and R Shiny resulted in a simple Shiny app where the user can upload a flower image, the system will then predict the flower species.

Steps that I took

  1. Download labeled flower data from the Visual Geometry Group,
  2. Install Pytorch and download their transfer learning tutorial script,
  3. You need to slightly adjust the script to work on the flower data,
  4. Train and Save the model as a (*.pt) file, 
  5. Using the R reticulate package you can call python code from within R so that you can use a pytorch models in R,
  6. Create a Shiny app that allows the user to upload an image and display the predicted flower species.

Some links

Github repo with: Python notebook to fine tune the resnet18 model, R script with Shiny App, data folder with images.

Live running shiny app can be found here. 

Cheers, Longhow

XSV tool

From time to time you do get large csv files. Take for example the open data from RDW with all the vehicles in The Netherlands. The size is ~ 7.6 GB (14 mln. rows and 64 columns), its not even really that large, but large enough for notepad, wordpad and Excel to hang….

There is a nice and handy tool XSV, see the github repo.

You can use it for some quick stats of the csv file and even some basic manipulations. For my csv file,  It takes around 17 secs to count the number of records, around 18 secs to aggregate on a column.

In R data.table it took 2 minutes to import the set and in  Python pandas 2.5 minutes

#CommandlineToolsAreStillCool #XSV #CSV

Selection_070

Deploy machine learning models with GKE and Dataiku

dataikukubernetes01

Introduction

In a previous post I described how easy it is to create and deploy machine learning models (exposing them as REST APIs) with Dataiku. In particular, it was an XGboost model predicting home values. Now, suppose my model for predicting home values becomes so successful that I need to serve millions of request per hour, then it would be very handy if my back end scales easily.

In this brief post I outline the few steps you need to take to deploy machine learning models created with Dataiku on a scalable kubernetes cluster on Google Kubernetes Engine (GKE).

Create a Kubernetes cluster

There is a nice GKE quickstart that demonstrate the creation of a kubernetes cluster on Google Cloud Platform (GCP). The cluster can be created by using the GUI on the Google cloud console. Alternatively, if you are making use of the Google cloud SDK, it basically boils down to creating and getting credentials with two commands:

gcloud container clusters create myfirst-cluster
gcloud container clusters get-credentials myfirst-cluster

When creating a cluster, there are many options that you can set. I left all options at their default value. It means that only a small cluster of 3 nodes of machine type n1-standard-1 will be created. We can now see the cluster in the Google cloud console.

dataikukubernetes03

Setup the Dataiku API Deployer

Now that you have a kubernetes cluster we can easily deploy predictive models with Dataiku. First, you need to create a predictive model. As described in my previous blog, you can do this with the Dataiku software. Then the Dataiku API Deployer, is the component that will take care of the management and actual deployment of your models onto the kubernetes cluster.

The machine where the Dataiku API Deployer is installed must be able to push docker images to your Google cloud environment and must be able to interact with the kubernetes cluster (through the kubectl command).

dataikukubernetes02

Deploy your stuff……

My XGboost model created in Dataiku is now pushed to the Dataiku API Deployer. From the GUI of the API Deployer you are now able to select the XGboost model to deploy it on your kubernetes cluster.

The API Deployer is a management environment to see what models (and model versions) are already deployed, it checks if the models are up and running, it manages your infrastructure (kubernetes clusters or normal machines).

dataikukubernetes04

When you select a model that you wish to deploy, you can click deploy and select a cluster. It will take a minute or so to package that model into a Docker image and push it to GKE. You will see a progress window.

dataikukubernetes05

When the process is finished you will see the new service on your Kubernetes Engine on GCP.

dataikukubernetes06

The model is up and running, waiting to be called. You could call it via curl for example:

curl -X POST \
  http://35.204.180.188:12000/public/api/v1/xgboost/houseeprice/predict \
  --data '{ "features" : {
    "HouseType": "Tussenwoning",
      "kamers": 6,
      "Oppervlakte": 134,
      "VON": 0,
      "PC": "16"
  }}'

Conclusion

That’s all it was! You now have a scalable model serving engine. Ready to be easily resized when the millions of requests start to come in….. Besides predictive models you can also deploy/expose any R or Python function via the Dataiku API Deployer. Don’t forget to shut down the cluster to avoid incurring charges to your Google Cloud Platform account.

gcloud container clusters delete myfirst-cluster

Cheers, Longhow.

Google AutoML rocks!

Waaauw Google AutoML Vision rocks!

A few months ago I performed a simple test with Keras to create a Peugeot – BMW image classifier on my laptop.

See Is that a BMW or a Peugeot?

A friendly encouragement from Erwin Huizenga to try Google AutoML Vision resulted in a very good BMW-Peugeot classifier 10 minutes later without a single line of code. Just a few simple steps were needed.

  • Upload your car images and label them.

wp1

  • Click train (first hour of training is for free!)
  • After 10 minutes the model was trained, with very good precision and recall.

wp2

And the nice thing: The model is up-and-running for anyone or any client application who needs an image prediction.

wp3.png

Just give it a try……Google AutoML Vision!