Custom blocks are cloud jobs that can be hosted and used on Edge Impulse. They serve a dedicated task, are extremely flexible, let you customize your experience and fasten your time-to-market.
Creating a transformation block - to fetch, sort, validate, combine and transform existing data into robust datasets that can be imported into your projects.
Building and hosting custom DSP blocks - to create and host your custom signal processing techniques and use them directly in your projects.
Create a custom learning block - to use your custom models and load pre-trained weights with PyTorch, Keras or scikit-learn.
Building deployment blocks - to create custom deployment targets for your products.
Transformation blocks are very flexible and can be used for most advanced use cases.
They can either take raw data from your organizational datasets and convert the data into files that can be loaded in an Edge Impulse project/another organizational dataset. But you can also use the transformation blocks as cloud jobs to perform specific actions using standalone mode.
Transformation blocks are available in your organization pipelines and in your project pipelines so you can automate your processes.
You can use transformation blocks to fetch external datasets, augment/create variants of your data samples, generate synthetic datasets, extract metadata from config files, create helper graphs, align and interpolate measurements across sensors, or remove duplicate entries. The possibilities are endless.
Transformation blocks can be written in any language, and run on Edge Impulse infrastructure.
Only available with Edge Impulse Enterprise Plan
Try our FREE Enterprise Trial today.
Transformation blocks can be complex to set up and are one of the most advanced features Edge Impulse provides. Feel free to ask your customer solution engineer for some help and some examples, we have been setting up complex pipelines for our customers and our engineers have acquired a lot of expertise with transformation blocks.
You can run your transformation blocks as transformation jobs. They can be triggered:
from your organization:
From this view, Custom blocks->Transformation
From the Data transformation
From the Data pipelines
from your projects:
From the Data sources (Standalone transformation blocks only)
By default, we provide several pre-built transformation blocks that you can use directly in your organization or your organization's projects.
We will add more over time when we see a recurring need or interest. The current ones are the following:
A transformation block consists of a Docker image that contains one or several scripts. The Docker image is encapsulated in the transformation block with additional parameters.
Here is a minimal configuration for the transformation blocks:
In this documentation page, we will explain how to setup a transformation block and will explain the different options.
You can directly create your transformation block within Edge Impulse Studio from a public Docker image or import existing transformation blocks:
Example repository
You can find several transformation block examples in this Github repository. These are a great way to get started, either by importing them directly in your organization or by using them as a getting-started template.
To run the data transformation jobs, see the Data transformation documentation page.
To setup your block, an easy method is to use the Edge Impulse CLI command, edge-impulse-blocks init
:
Tip: If you want to access your bucket, make sure to press <space>
to select the bucket attached to your organization.
The step above will create the following .ei-block-config
in your project directory:
To push your transformation block, simply run edge-impulse-blocks push
.
At Edge Impulse, we mostly use Python, Javascript/Typescript and Bash scripts, but you can write your transformation blocks in any language.
Dockerfile example to trigger a Bash script:
Dockerfile example to trigger a Python script and install the required dependencies:
The Dockerfile above describes a base image (Python 3.7.5), the Python dependencies (in requirements.txt
) and which script to run (transform.py
).
Note: Do not use a WORKDIR
under /home
! The /home
path will be mounted in by Edge Impulse, making your files inaccessible.
ENTRYPOINT vs RUN / CMD
If you create a custom Dockerfile, make sure to use ENTRYPOINT
to specify the application to execute, rather than RUN
or CMD
.
If you want to host your docker image on an external registry, you can use Docker Hub and use the username/image:tag
in the Docker container field.
We provide three modes to access your data:
In the Standalone mode, no data is passed to the container, but you can still access data by mounting your bucket onto the container.
At the Data item level, we pass the --in-directory
and --out-directory
arguments. The transformation jobs will run on each directory present in your selected path. These jobs can run in parallel.
At the file level, we pass the --in-file
and --out-directory
arguments. The transformation jobs will run on each file present in your selected path. These jobs can run in parallel.
Note that for the two last operation modes, you can use query filters to only include certain data items and certain files.
The stand-alone method is the most flexible option (it can work on both generic and clinical datasets). You can consider this transformation block as a cloud job that you can use for anything in your machine learning pipelines.
Please note that this mode does not support running jobs in parallel, as it is unknown in advance how many files or how many directories are present in your dataset.
To access your data, you must mount your bucket/upload portal into the container, you can do this both when setting up your transformation block using Edge Impulse CLI, or directly in the studio when creating/editing a transformation block.
You can use custom blocks parameters to retrieve the bucket name and the required directory to access your files programmatically.
Examples
--in-directory
)When selecting the Data item operation mode, two parameters will be passed to the container:
--in-directory
--out-directory
The transformation jobs will run on each "Data item" (directory) present in your selected path or dataset.
--in-file
)When selecting the File operation mode, two parameters will be passed to the container:
--in-file
--out-directory
The transformation jobs will run on each file present in selected path.
When editing your block on Edge Impulse Studio, you can set the number of desired CPUs and the memory needed for your container to run properly. Likely, you can set the limits of the same parameters.
You can update the metadata of blocks directly from a transformation block by creating a ei-metadata.json
file in the output directory. The metadata is then applied to the new data item automatically when the transform job finishes. The ei-metadata.json
file has the following structure:
Some notes:
If action
is set to add
the metadata keys are added to the data item. If action
is set to replace
all existing metadata keys are removed.
When using the CLI to setup your block, by default we mount your bucket with the following mounting point:
You can change this value if you want your transformation block to behave differently.
See adding parameters to custom blocks dedicated documentation page.
Transformation blocks get access to the following environmental variables, which let you authenticate with the Edge Impulse API. This way you don't have to inject these credentials into the block. The variables are:
EI_API_KEY
- an API key with 'member' privileges for the organization.
EI_ORGANIZATION_ID
- the organization ID that the block runs in.
EI_API_ENDPOINT
- the API endpoint (default: https://studio.edgeimpulse.com/v1).
Label image data using GPT-4o: Label image data using GPT-4o block
Text to speech transform block (Javascript): GitHub
Fetch a dataset hosted on Kaggle (Python): Github
Generate graph from sensor csv data (Python): Github
Hello Edge (Bash): Github
--in-file
)Mix background noise into audio files (Bash script): GitHub
Access your data - Helper transformation block (Python): Github
Resample CSV (Python): Github
--in-directory
)Access your data - Helper transformation block (Python): Github
Check file existence - Add ei_check metadata on file existence (Python): Github
Merge CSV files - Merge CSV files on a given key (Python): Github
Merge audio and CSV - Merge audio file and time-series CSV (Python): Github
Now that you have a better idea of what are transformation blocks, here is a graphical recap of how it works:
The job run indefinitely
If you notice that your jobs run indefinitely, it is probably because of an error or the script has not been properly terminated. Make sure to exit your script with code 0 (return 0
, exit(0)
or sys.exit(0)
) for success or with any other error code for failure.
Cannot access files in bucket
If you cannot access your files in your bucket, make sure that the mount point is properly configured.
When using the CLI, it is a common mistake to forget pressing <space>
key to select the bucket attached to your organization.
Job failed without logs (only Job failed)
It probably means that we had an issue when triggering the container. In many cases it is related with the issue above, the mount point not being properly configured.
I cannot access the logs
We are still investigating why all the logs are not displayed properly. If you are using Python, you can also flush stdout after you print it using something like print("hello", flush=True)
.
Can I host my Docker image on Docker Hub?
Yes, you can. You can test this Standalone transformation block if you'd like: luisomoreau/hello_edge:latest
Also, make sure to configure the additional block parameters with this config:
It will print "hello +name" on the transformation job logs.
This is the specification for the deployment-metadata.json
file from .
One of the most powerful features in Edge Impulse are the built-in deployment targets (under Deployment in the Studio), which let you create ready-to-go binaries for development boards, or custom libraries for a wide variety of targets that incorporate your trained impulse. You can also create custom deployment blocks for your organization. This lets developers quickly iterate on products without getting your embedded engineers involved, lets your customers build personalized firmware using their own data, or lets you create custom libraries.
In this tutorial you'll learn how to use custom deployment blocks to create a new deployment target, and how to make this target available in the Studio for all users in the organization.
Only available with Edge Impulse Enterprise Plan
Try our FREE today.
You'll need:
The .
If you receive any warnings that's fine. Run edge-impulse-blocks
afterwards to verify that the CLI was installed correctly.
Deployment blocks use Docker containers, a virtualization technique which lets developers package up an application with all dependencies in a single package. If you want to test your blocks locally you'll also need (this is not a requirement):
installed on your machine.
Then, create a new folder on your computer named custom-deploy-block
.
When a user deploys with a custom deployment block two things happen:
A package is created that contains information about the deployment (like the sensors used, frequency of the data, etc.), any trained neural network in .tflite and SavedModel formats, the Edge Impulse SDK, and all DSP and ML blocks as C++ code.
This package is then consumed by the custom deployment block, which can incorporate it with a base firmware, or repackage it into a new library.
If you now go to the Deployment page, a new option appears under 'Create library':
Once you click Build you'll receive a ZIP file containing five items:
trained.tflite
- if you have a neural network in the project this contains neural network in .tflite format. This network is already fully quantized if you choose the int8
optimization, otherwise this is the float32
model.
trained.savedmodel.zip
- if you have a neural network in the project this contains the full TensorFlow SavedModel. Note that we might update the TensorFlow version used to train these networks at any time, so rely on the compiled model or the TFLite file where possible.
model-parameters
- impulse and block configuration in C++ format. Can be used by the SDK to quickly run your impulse.
tflite-model
- neural network as source code in a way that can be used by the SDK to quickly run your impulse.
Store the unzipped file under custom-deploy-block/input
.
With the basic information in place we can create a new deployment block. Here we'll build a standalone application that runs our impulse on Linux, very useful when running your impulse on a gateway or desktop computer. First, open a command prompt or terminal window, navigate to the custom-deploy-block
folder (that you created under 1.), and run:
This will prompt you to log in, and enter the details for your block.
Unzip under custom-deploy-block/app
.
To build this application we need to combine the application with the edge-impulse-sdk
, model-parameters
and tflite-model
folder, and invoke the (already included) Makefile.
To build the application we use Docker, a virtualization technique which lets developers package up an application with all dependencies in a single package. In this container we'll place the build tools required for this application, and scripts to combine the trained impulse with the base application.
First, let's create a small build script. As a parameter you'll receive --metadata
which points to the deployment information. In here you'll also get information on the input and output folders where you need to read from and write to.
Create a new file called custom-deploy-block/build.py
and add:
build.py
Next, we need to create a Dockerfile, which contains all dependencies for the build. These include GNU Make, a compiler, and both the build script and the base application.
Create a new file called custom-deploy-block/Dockerfile
and add:
Dockerfile
To test the build script we first build the container, then invoke it with the files from the input
directory. Open a command prompt or terminal, navigate to the custom-deploy-block
folder and:
Build the container:
Invoke the build script - this mounts the current directory in the container under /home
, and then passes the downloaded metadata script to the container:
Or if you run Windows or macOS, you can use Docker to run this application:
With the deployment block ready you can make it available in Edge Impulse. Open a command prompt or terminal window, navigate to the folder you created earlier, and run:
This packages up your folder, sends it to Edge Impulse where it'll be built, and finally is added to your organization. The transformation block is now available in Edge Impulse under Deployment blocks. You can go here to set the logo, update the description, and set extra command line parameters.
The deployment block is automatically available for all organizational projects. Go to the Deployment page on a project, and you'll find a new section 'Custom targets'. Select your new deployment target and click Build.
And now you'll have a freshly built binary from your own deployment block!
Custom deployment blocks are a powerful tool for your organization. They let you build binaries for unreleased products, let you package up impulse as custom libraries, or can let your customers deploy to private targets (if you add an external collaborator to a project they'll have access to the blocks as well). Because the deployment blocks are integrated with your project, and hosted by Edge Impulse this lets everyone, from FAE to R&D developer, now iterate on on-device models without getting your embedded engineers involved.
deployment-metadata.json
- this contains all information about the deployment, like the names of all classes, the frequency of the data, full impulse configuration, and quantization parameters. A specification can be found here: .
edge-impulse-sdk
- a copy of the latest .
Next, we'll add the application. The base application can be found at .
.
Voila. You now have an output
folder that contains a ZIP file. Unzip output/deploy.zip
and now you have a standalone application which runs your impulse. If you run Linux you can invoke this application directly (grab some data from 'Live classification' for the features, see ):
Deployment blocks do not have access to the internet by default. If you need this, or if you need to pull additional information from the project (e.g. access to DSP blocks) you can set the 'privileged' flag on a deployment block. This will enable outside internet access, and will pass in the project.apiKey
parameter in the (if a development API key is set) that you can use to authenticate with the .
You can also use custom deployment blocks with the other organizational features, and can use this to set up powerful pipelines automating , , training new impulses and then deploying back to your device - either through the UI, or via the API. If you're interested in deployment blocks or any of the other enterprise features,