LogoLogo
HomeDocsAPIProjectsForum
  • Release Notes
  • Release Notes (2024)
  • Release Notes (2023)
  • Release Notes (2022)
Powered by GitBook
On this page
  • v1.66.0
  • v1.65.4
  • v1.65.2
  • v1.65.1
  • v1.64.5
  • v1.64.3
  • v1.64.2
  • v1.64.1
  • v1.64.0
  • v1.63.3
  • v1.63.2
  • v1.63.1
  • v1.62.0
  • v1.61.37
  • v1.61.35
  • v1.61.34
  • v1.61.32
  • v1.61.31
  • v1.61.30
  • v1.61.29
  • v1.61.25
  • v1.61.24
  • v1.61.23
  • v1.61.22
  • v1.61.21
  • v1.61.20
  • v1.61.19
  • v1.61.18
  • v1.61.17
  • v1.61.16
  • v1.61.15
  • v1.61.12
  • v1.61.11
  • v1.61.9
  • v1.61.8
  • v1.61.7
  • v1.61.6
  • v1.61.5
  • v1.61.3
  • v1.60.16
  • v1.60.14
  • v1.60.13
  • v1.60.11
  • v1.60.10
  • v1.60.8
  • v1.60.7
  • v1.60.5
  • v1.60.4
  • v1.60.3
  • v1.60.2
  • v1.60.1
  • v1.60.0
  • v1.59.6
  • v1.59.5
  • v1.59.4
  • v1.59.0
  • v1.58.0
  • v1.57.18
  • v1.57.17
  • v1.57.12
  • v1.57.11
  • v1.57.10
  • v1.57.7
  • v1.57.6
  • v1.57.5
  • v1.57.4
  • v1.57.3
  • v1.57.2
  • v1.57.1
  • v1.57.0
  • v1.56.15
  • v1.56.13
  • v1.56.12
  • v1.56.11
  • v1.56.9
  • v1.56.6
  • v1.55.1
  • v1.55.0
  • v1.54.5
  • v1.54.3
  • v1.54.2
  • v1.54.1
  • v1.54.0
  • v1.53.14
  • v1.53.11
  • v1.53.9
  • v1.53.8
  • v1.53.7
  • v1.53.6
  • v1.53.5
  • v1.53.4
  • v1.53.3
  • v1.53.2
  • v1.53.1
  • v1.52.13
  • v1.52.12
  • v1.52.10
  • v1.52.7
  • v1.51.3
  • v1.51.0
  • v1.50.18
  • v1.50.16
  • v1.50.15
  • v1.50.14
  • v1.50.13
  • v1.50.12
  • v1.50.8
  • v1.50.6
  • v1.50.4
  • v1.50.1
  • v1.49.39
  • v1.49.34
  • v1.49.32
  • v1.49.31
  • v1.49.29
  • v1.49.27
  • v1.49.26
  • v1.49.25
  • v1.49.24
  • v1.49.23
  • v1.49.19
  • v1.49.16
  • v1.49.10
  • v1.49.5
  • v1.49.12
  • v1.49.3
  • v1.49.0
  • v1.48.7
  • v1.48.2
  • v1.48.1
  • v1.48.0
  • v1.47.3
  • v1.47.1
  • v1.47.0
  • v1.46.4
  • v1.46.2
  • v1.46.0
  • v1.45.4
  • v1.45.3
  • v1.44.5
  • v1.44.4
  • v1.44.3
  • v1.44.1
  • v1.44.0
  • v1.43.5
  • v1.43.3
  • v1.42.2
  • v1.42.1
  • v1.42.0
  • v1.41.1
  • v1.40.13
  • v1.40.12
  • v1.40.11
  • v1.40.10
  • v1.40.9
  • v1.40.8
  • v1.40.7
  • v1.40.1
  • v1.40.0
  • v1.39.4

Release Notes (2024)

PreviousRelease NotesNextRelease Notes (2023)

Last updated 3 months ago

v1.66.0

December 24, 2024

  • Updates to Renesas targets and RZ/V2H GA

v1.65.4

December 23, 2024

  • STM32 N6 default firmware update

v1.65.2

December 21, 2024

  • Updates to STM32 N6 firmware

  • Fixes for 'shuffled axis, resampled, multiple DSP blocks modifies the impulse'

v1.65.1

December 21, 2024

  • EON tuner settings dialog UX fixes

  • EON Tuner extend search tweaks

  • Update Image DSP in Studio

v1.64.5

December 19, 2024

v1.64.3

December 18, 2024

v1.64.2

December 17, 2024

v1.64.1

December 17, 2024

v1.64.0

December 17, 2024

v1.63.3

December 14, 2024

v1.63.2

December 12, 2024

v1.63.1

December 11, 2024

v1.62.0

December 9, 2024

v1.61.37

December 9, 2024

v1.61.35

December 5, 2024

v1.61.34

December 4, 2024

v1.61.32

December 3, 2024

v1.61.31

December 2, 2024

v1.61.30

November 30, 2024

v1.61.29

November 29, 2024

v1.61.25

November 26, 2024

v1.61.24

November 25, 2024

v1.61.23

November 21, 2024

v1.61.22

November 19, 2024

v1.61.21

November 19, 2024

v1.61.20

November 18, 2024

v1.61.19

November 18, 2024

v1.61.18

November 18, 2024

v1.61.17

November 13, 2024

v1.61.16

November 13, 2024

v1.61.15

November 12, 2024

v1.61.12

November 11, 2024

v1.61.11

November 11, 2024

v1.61.9

November 9, 2024

v1.61.8

November 8, 2024

v1.61.7

November 5, 2024

v1.61.6

November 5, 2024

v1.61.5

November 4, 2024

v1.61.3

November 4, 2024

v1.60.16

October 31, 2024

v1.60.14

October 29, 2024

v1.60.13

October 27, 2024

v1.60.11

October 25, 2024

v1.60.10

October 24, 2024

v1.60.8

October 23, 2024

v1.60.7

October 19, 2024

v1.60.5

October 16, 2024

v1.60.4

October 15, 2024

v1.60.3

October 14, 2024

v1.60.2

October 11, 2024

v1.60.1

October 10, 2024

v1.60.0

October 8, 2024

v1.59.6

October 7, 2024

v1.59.5

October 4, 2024

v1.59.4

October 2, 2024

v1.59.0

September 30, 2024

v1.58.0

September 19, 2024

v1.57.18

September 17, 2024

v1.57.17

September 17, 2024

v1.57.12

September 13, 2024

v1.57.11

September 12, 2024

v1.57.10

September 5, 2024

v1.57.7

August 29, 2024

v1.57.6

August 29, 2024

v1.57.5

August 28, 2024

v1.57.4

August 28, 2024

v1.57.3

August 27, 2024

v1.57.2

August 26, 2024

v1.57.1

August 22, 2024

v1.57.0

August 21, 2024

v1.56.15

August 20, 2024

v1.56.13

August 15, 2024

v1.56.12

August 15, 2024

    • Added the ability to create a new experiment when making changes to an existing impulse

    • Added flag that marks an impulse as stale following a change to the dataset

    • Added filtering to Experiments table

v1.56.11

August 15, 2024

v1.56.9

August 13, 2024

v1.56.6

August 7, 2024

v1.55.1

August 2, 2024

v1.55.0

July 30, 2024

    • This Impulse design overhaul will enhance your model workflows and accelerate your project development cycles by allowing users to experiment with different impulses simultaneously, along with many other upgrades.

v1.54.5

July 24, 2024

v1.54.3

July 19, 2024

v1.54.2

July 18, 2024

v1.54.1

July 18, 2024

v1.54.0

July 17, 2024

v1.53.14

July 12, 2024

v1.53.11

July 9, 2024

v1.53.9

July 6, 2024

v1.53.8

July 5, 2024

v1.53.7

July 4, 2024

v1.53.6

July 4, 2024

v1.53.5

July 2, 2024

v1.53.4

July 1, 2024

v1.53.3

July 1, 2024

v1.53.2

June 28, 2024

v1.53.1

June 28, 2024

v1.52.13

June 26, 2024

v1.52.12

June 26, 2024

v1.52.10

June 21, 2024

v1.52.7

June 19, 2024

v1.51.3

June 11, 2024

v1.51.0

June 7, 2024

v1.50.18

June 4, 2024

v1.50.16

June 3, 2024

v1.50.15

June 3, 2024

v1.50.14

May 30, 2024

v1.50.13

May 30, 2024

v1.50.12

May 27, 2024

v1.50.8

May 25, 2024

v1.50.6

May 23, 2024

v1.50.4

May 22, 2024

v1.50.1

May 21, 2024

v1.49.39

May 17, 2024

v1.49.34

May 16, 2024

v1.49.32

May 15, 2024

v1.49.31

May 14, 2024

v1.49.29

May 13, 2024

v1.49.27

May 13, 2024

v1.49.26

May 10, 2024

v1.49.25

May 10, 2024

v1.49.24

May 9, 2024

v1.49.23

May 7, 2024

v1.49.19

May 1, 2024

v1.49.16

April 29, 2024

  • Various performance improvements and bug fixes

v1.49.10

April 17, 2024

v1.49.5

April 15, 2024

  • Various bug fixes

v1.49.12

April 23, 2024

v1.49.3

April 9, 2024

v1.49.0

April 2, 2024

v1.48.7

March 27, 2024

v1.48.2

March 18, 2024

v1.48.1

March 14, 2024

v1.48.0

March 14, 2024

v1.47.3

March 12, 2024

v1.47.1

March 8, 2024

v1.47.0

March 8, 2024

v1.46.4

February 29, 2024

v1.46.2

February 27, 2024

v1.46.0

February 26, 2024

v1.45.4

February 17, 2024

v1.45.3

February 16, 2024

v1.44.5

February 12, 2024

v1.44.4

February 12, 2024

v1.44.3

February 9, 2024

v1.44.1

February 8, 2024

v1.44.0

February 6, 2024

v1.43.5

February 5, 2024

v1.43.3

February 2, 2024

v1.42.2

January 20, 2024

v1.42.1

January 18, 2024

v1.42.0

January 18, 2024

v1.41.1

January 17, 2024

v1.40.13

January 17, 2024

v1.40.12

January 13, 2024

v1.40.11

January 10, 2024

v1.40.10

January 10, 2024

v1.40.9

January 9, 2024

v1.40.8

January 9, 2024

v1.40.7

January 8, 2024

v1.40.1

January 5, 2024

v1.40.0

January 4, 2024

v1.39.4

January 3, 2024

Store resampling metadata in json

Bayesian tuner metadata

Avoid job_states "version" column limit

Allow user-defined objective weights for EON tuner Bayesian search

Updates for Renesas RZ targets

Fixes for projects with no collaborators

Release Azure Blob Storage support

Bayesian tuner warnings fix

Fixed KeyError exception in import_metrics for certain search spaces

* Display zero padding in the raw data graph in DSP page

Custom model placement in the firmware memory

Fix Arduino CLI version check in flashing scripts

Filter EON tuner runs list to show only the latest run

EON Tuner - fix mixed types

Experiments: Column settings modal scrollable

Use light gray icon for keys copy button

Add missing space in "split sample into frames" job logs

Update image input scaling list labels

CEVA NeuPro Nano profiling tools integration

Improve performance in large regression projects

Make latency estimation on BYOM page match deployment page

Make all initializer clauses explicit for ESP32 conv kernels

EfficientNetV2B0 grayscale weights

More OOM fixes for patchcore on large datasets

Enable Bayesian search without advanced EON tuner experiment enabled

Sanitize labels/axes properly before passing to Python

Fix license file in public EI SDK

Early detect when info.labels file is not valid JSON

Added 'disableConstraints' and 'disableDeduplicate' to advanced EON tuner config

Run Patchcore feature extraction on batches and memmap on large datasets

Fix 'element not interactable' in BYOM tests

Cut down the size of the DSP Server by a few GB

Print results function for postprocessing / counting tracking SDK follow-up items

Patchcore disable debug calculation that causes OOM on larger datasets

Fix for reshape error in FOMO evaluation

Modifying __PKHBT patch macro in CMSIS

Allow setting explicit validation set

Add 25hz support and C interface to PPG lib

Python SDK - Bump version to 1.0.18

Added 19 more datasets to Python SDK

Spectral Analysis Autotuner V2

Include owner name when searching public projects

Update DSP profiling when target changes

Print results function for postprocessing / counting tracking SDK follow-up items

Support additional mount points for synthetic data/AI Labeling blocks

Linux CLI: More descriptive error msgs when unexpected API keys provided

Add reset to Nordic flashing scripts

Make .eim deployments searchable by 'eim'

Remove extra dependancies on model_variables.h from SDK files

Added support for keras 3

Make downloadable block outputs available on public project views

Fix public data explorer

AI Labeling release

Check out the !

Update ESP NN to add ESP32-P4

DSP getFeatureMetadata: improve logic to patch missing featureLabels

Move Linux CLI common code to separate modules

Expose Vela-compiled model in the dashboard

Add nxp-imx93-cpu constraints

Fix OpenAPI generator code for api-bindings/node

Account for missing size property in downloadable artefacts

Fix partial DSP with very large projects

Fix model_compiler issue with flattened input data

Fix training with Syntiant + noise augmentation

Require at least 1 sample when starting EON tuner

Add public badge to organization projects list

Allow editing bounding boxes directly in the data acquisition grid

Minor impulse experiments tweaks

Group download artefacts by impulse

Fix navbar animation on Chrome

Minor enhancement allowing inference image as part of IoTCore payload

Clarify copy around retraining models via data pipeline

Remove classes/labels from impulse summary to speed up regression projects

Raw data processing daemon fixes

Fix patchcore training OOM

Fix classical ml blocks metrics error

Map to correct property when sorting on public projects view

Linux CLI: ArduCam support on RPi 5 with Bookworm OS

Allow disabling 'Model testing' during versioning

Move toggle'able items in dropdown lists to checkboxes

Fix for AWS greengrass usage with silent option

Add sorting to public projects endpoint

Download Impulse experiments as CSV

Add anomaly head profiling to the memory performance

Implement object tracking/counting in EI SDK

Fixed undefined exception on reading 'inputBlocks'

Run batch sample operations on large datasets within a job

Add support for RPi bookworm & Microchip SAMA7 on Yocto

Fix prediction positions in fit-long overlay comparison

Show experiment source (Manual vs from EON Tuner)

Fix EON Tuner for input type 'features'

Remove .gitmodules from Alif firmware

Change "tags" UI in impulse list to be more compact

Fix raw features order on live classify

Show ms in validation page if below one sec

Add `includes' to Arduino library properties

Fix the numbers by the icons in the EON tuner results for PatchCore

Data acquisition: small ID column changes

Ensure samples use DSP block axis order during feature generation

Implemented batch metadata updates in data acquisition

Implemented new EON tuner objective selection

Re-introduce tuner link to left navbar

Enable YOLOv5 for Himax WiseEye2

Add a helper function for users to resize matching Studio resize

Fix regression on YOLOV5 for DRP-AI

Make HR/HRV block available for all users

Check out the !

Add Int8 inference during training of FOMO-AD-Patchcore

Move all custom block configs to parameters.json

Adds more grayscale weights for MobileNetV2

Add multi-label support for SA and specgram autotuner

Support expanded view in live classification for visual AD result image

Allow keeping same order when uploading items in the UI

Release PatchCore for FOMO-AD for Visual Anomaly Detection learning block

Check out the !

Better BYOM navigation from dashboard

Show all available model types on model testing/live classification

Inform users when new impulse is not visible due to table filters

Notify users of CSV wizard config before uploading file

Fix live classification for projects with unused DSP blocks

Alif: add nproc info for MAC

Add SD card for BrickML

Add RAM/ROM estimates in the descriptions for visual AD backbones

Particle limit status readout during init

Ambiq Apollo4 integration

Support all resize methods in object detection overlay

Tabular data ingestion

View the !

Update to Openmv firmware and python scripts

Improvements to user experience with organization buckets

Add ability to add tags to impulse experiments

Add multilabel upload to Python SDK

Invalidate model testing summary when dataset changes

Add Syntiant DSP support to EON tuner

Add resize mode to exports and Linux runner

Added visual anomaly search space template to EON Tuner

Add support for multiple learn block in the EON Tuner

Update Vela compiler to 3.12.0

Update to sign-up flow

Show test set accuracy for regression and visual anomaly detection

Updated full tflite to 2.16.1 and added Mac M1 libraries

Add support for TAO models (i.e. SSD, RetinaNet, YOLOv3 and YOLOv4) for Ethos Linux inferencing engine

Added Raspberry Pi 5 as a new target

Alif new camera support

Add support for non-timeseries features

Impulse experiments improvements:

Make an explicit copy button for API/HMAC keys

Restore CMSIS NN optimizations for M0(+) MCUs for x2 INT8 speedup

Onnx2tf upgrade

Add scatter_nd, reduce_any, reduce_all ops

Fixed EON tuner trials failing when project contains only training dataset and no test dataset

Fix inference results on Himax WiseEye2 using Ethos

HD FOMO-AD

Impulse Experiments

Check out the !

Nicla OpenMV Runtime fix

Himax WiseEye2 (aka Grove Vision AI Module V2) integration

View the !

Microphone integration for Alif gen2

Allow custom learn blocks to specify output files

Python SDK - Add build() function to build impulse

Release EON tuner regression support

DSP Autotuner: padding, multi-label fixes + pass sample labels

Show label options in upload UI when 'unlabeled' selected

Make the Ethos U55-64 deployment public

Allow pro users to deploy classical ML

Alif gen2 IMU integration

Hide "items" for default dataset pipelines

Adds HRV and Motion Artifact Removal to HR DSP block

Retain filename when processing CSV data

Allow for JPEG images in SNAPSHOTSTREAM and SNAPSHOT mode

Release Synthetic data tab for pro users

Check out the !

Remove pro tier feature flag and user experiment

CSV Wizard: add support for one sensor value per row (same sample spanning multiple rows)

Update Arduino scripts

Linux CLI: Fix runner downloader for non-jetpack 6.0

Generate TVM library/EIM as standalone

Admin panel: jobs list on user, project and organization views

Fix exception on deployment for FOMO AD and EON RAM optimized mode

Show exact timestamp in grid view, synthetic data, model testing

Linux CLI: infer and automatically download for JetPack 6.0

Remove BETA badge and whitelisting for Microchip SAMA7G54 deploy option

Fix project search via WL admin API

Move perfcal graph back to scatter chart

Memryx aarch64 EIM support

Add Orin Inference and Build Container for JetPack 6.0

Think Silicon NEOX® AI SDK & GA100 RISC-V GPGPU

View the !

Added latency estimation for Microchip SAMA7G54

View auto-labeler segment improvements

Added Visual AD output to Arduino sketches

Fix wavelet visualization bug

Increase Jetson deployment memory

Add RZ/V2L TVM EIM deployment

Enable EON RAM Optimized mode on Arduino/Particle

EON Tuner: fix model testing, respect zero padding

Ensure tooltip targets are specified correctly

Model testing: Return 'float32' model variant when all blocks are anomaly

Fix Units of "By Frequency" slider from ms to Hz

Added yml to ethos pack deployment

Enable run static impulse in Sony firmware

Use aligned buffer for Nicla Vision framebuffer (ingestion fix)

For CMSIS pack also deploy a model.clayer.yml file

Anomaly block: min. confidence rating resets to 0 every time you train

Printf float for anomaly

Add Microchip SAMA7G54 deploy option to studio

Allow viewing where a segment came from in auto-segmenter

Launch of the , designed to bridge the gap between the Community and Enterprise plans!

Akida Models part of EON Tuner Search Space

himax-flash-tool: Add support for Grove Vision AI Module V2

Fix 'this model won't run on MCU' for random forest binary classification

Ethos pack deployment

Fix to EON-compiled Ethos deployment

Properly sanitize labels when passing to Python/C++ code

Add performance calculation for HRV block

Fix feature explorer on restored projects

nRF7002DK Public Release

View the !

Use model threshold in mobile client instead of hardcoded values

More RAM for Seeed Sensecap

Add an optional mask to org header images

Improvements for when we copy data from DSP->Learn, when we re-split data

Various Python SDK fixes

Reduce resources for admin api/panel

Reduce mobile client memory consumed

Add sorting to the project list

Fix regression y_true values for model testing

Enable selecting model variant in live classification and model testing

Add 'save' button to Keras expert mode

BYOM - Move 'Test sample' up, so it's visible with many classes

Update Python SDK and Python API Bindings docs

Print current project in edge-impulse-uploader

IMU improvement for Syntiant NDP120

Allow toggling the square mask when training object detection models

Improved Live Classification and Performance Calibration performance

Fixed camera color issue for ESP32 Arduino sketches

Enable the toggling of the anomaly heatmap overlay in visual anomaly detection

Enabling multiple learning blocks deployment for all Arm Ethos-U accelerators

Visual Anomaly Detection (FOMO-AD)

View the !

Add websocket support to the Python SDK

YOLOv2 support in Akida inferencing engine

Multi-factor authentication

Make the 8 hour org job limit configurable in the UI

Add multilabel support to Python SDK

Improvements to resampling algorithm

Add EON Tuner support to Python SDK

Public transformation blocks

WASM SIMD deployment for NodeJS

Allow White Label admins to delete users

Jetson Orin

View the !

EON RAM optimized (patch-based inference) release. Minimize the RAM usage of the model to enable customers to execute more sophisticated and precise models with the same hardware resources.

Add support for Image scaling -128..127 for quantized image models

Make anomaly grid score responsive in mobile client

Show block name in training settings for custom blocks

Add display category for organization Transfer Learning blocks

Default datasets for organization transformations

Read the !

Basler cameras support in Linux CLI

Classical ML blocks

View the

Allow users to transfer expired trial projects to personal workspace

Allow guest users to access the Datasets view

Consistent color for bounding boxes

Adds back microphone support for MemryX

Add grid view to data acquisition

Add ability to list/unlist a public project

Use xterm to render job logs

RASyn board update

Speed up project restoration project

Add TAO integration (YOLOv3, YOLOv4, SSD and RetinaNet) in the embedded SDK

Improved classification view for object detection projects

Faster project versioning

Improve DSP parameters validation before feature generation

Allow filtering on ID in Data Acquisition

Add a 'Download source code' option to all custom blocks

Release Docker container Studio deployment option

Catch live classification with unsupported data

EON Compiler Subgraph Support

TAO SSD support

Python SDK - Update upload_pandas parameters, update readme and changelog

Add version information for EI-SDK pack

Launch VeLO for all enterprise customers

Add ID column to "Data acquisition"

Allow import/export CSV wizard config; and allow downloading original file used in CSV wizard

Added flatten DSP block support to EON tuner

Updated firmware for Arduino Nano 33

Add VeLO to EON Tuner and change name of config parameter

interval_ms should be a positive number, and should not be Infinity

Show EON Compiler toggle for GMM

EON Tuner fixes for custom ML blocks + autotuned blocks

Add OpenMV RT1062 to openmv lib deployment

Add more logging when sampling_freq missing

Fix for microphone ingestion for the Arduino Nano

Enabled camera sketch for Sony

Fix live classification for existing object detection models

Add CMSIS package deployment for Keil MDK

Add Studio version information to model_metadata.h

Downgrade arduino:mbed_nicla version to 3.4.1

Add 'Community' to 'Terms of Service' on signup pages

Generate and show logs for individual EON Tuner trials

documentation
announcement blog
announcement blog
announcement blog
feature announcement blog
documentation
documentation
public release announcement
Getting Started documentation
announcement blog
Getting Started documentation
documentation
announcement blog
"Professional Plan" pricing tier