Developer Relations / Coffee Machine Stages - Multi-label data Public

Classify new data

Classify existing test sample

Classifying ...

Waiting...

Cancel job

Classification result

Summary

Name

Name cannot be empty

Label

Category	Count

Detailed result

Show only unknowns

Raw data

Start classification to load...

Raw features

...

Spectral features

No features generated yet

Processed features

...

Anomaly explorer

For samples that are longer than the window length, a sliding window is used to classify the data multiple times. This setting determines the increase of the sliding window in milliseconds, for each step. This affects both live classification and model testing.

Mirror the setting from 'Create impulse' (500 ms.)

Enter a window increase (ms.):

Every learning block has a threshold. This can be the minimum confidence that a neural network needs to have, or the maximum anomaly score before a sample is tagged as an anomaly. You can configure these thresholds to tweak the sensitivity of these learning blocks. This affects both live classification and model testing.

Classifier

Minimum confidence rating

Anomaly detection (GMM)

Minimum score before tagging as anomaly

You can upload CBOR, JSON, CSV, WAV, JPG, PNG, AVI or MP4 files. You can also upload an annotation file named "info.labels" with your data to assign bounding boxes, labels, and/or metadata. View Uploader docs to learn more. Alternatively, you can use our Python SDK to programmatically ingest data in various formats, such as pandas or numpy.

For CSV files, configure the CSV Wizard to define how your files should be processed before uploading files.

Bounding boxes: You can upload object detection datasets in any supported format. Select both your images and the label file(s) when uploading to apply the labels.

Please give us some information about the data you are trying to upload.

Dataset annotation format

This field is required

Directory structure

This field is required

Label format

This field is required

Collect data directly from your phone, computer, device, or development board.

Device "" is now connected

Use the 'Classify new data' section to collect data from this device.

You can connect almost any device over serial using our data forwarder:

$ edge-impulse-data-forwarder

Or connect a supported device or development board:

We're always looking for ways to improve Edge Impulse. If you have any feedback, please let us know!

Subject

This field is required

How was your experience?

This field is required

You'll need a free Edge Impulse account to clone this project. Creating an account lets you add your own data, modify models, and join a community of thousands of embedded machine learning developers!

Target device

Define your target device requirements to inform model optimizations and performance calculations. No device yet? Use the default settings which you can change at any time.

Target device

Processor family

Clock rate

| MHz

Max

Custom device name

Application budget

Specify the available RAM and ROM for the model's operation, along with the maximum allowed latency for your specific application. Not sure yet? Start with the defaults and modify them later on.

RAM

| KB

Max

ROM

| KB

Max

Latency

| ms

Max

YEARLY

$400 /month

billed annually

SAVE 15%

MONTHLY

$475 /month

billed monthly

Classify new data

Classify existing test sample

Classifying ...

Classification result

Summary

Model variants

Detailed result

Raw data

Start classification to load...

Raw features

Spectral features

Processed features

Settings

Anomaly explorer

Distance from closest cluster