Release Notes (2022)

v1.14.29

December 14, 2022

v1.14.27

December 12, 2022

  • Allow DSP blocks to output WAVs

v1.14.19

December 5, 2022

v1.14.16

December 1, 2022

  • Bumped Arduino Nicla core version to 3.4.1

v1.14.15

December 1, 2022

  • Add an option to copy metadata (as passed in from a transform job)

v1.14.7

November 22, 2022

v1.14.5

November 20, 2022

v1.13.29

November 9, 2022

v1.13.23

October 25, 2022

  • Rename transferLearning to learning for CLI custom blocks instructions

v1.13.22

October 22, 2022

  • Add GPU accelerated inference Object Detection for Jetson

  • Arduino nano_ble33_sense_accelerometer_continuous fix

v1.13.21

October 20, 2022

  • ESP32 Update 3: Fixing ESP-NN Arduino library, minor bug fixes, update Arduino sketches

v1.13.21

October 20, 2022

  • ESP32 Update 3: Fixed ESP-NN Arduino library, minor bug fixes, Arduino sketches

v1.13.12

October 4, 2022

  • YOLOv5 inference version 3 update: inferencing available for full TFLite and DRP-AI

v1.13.8

October 3, 2022

  • Performance Calibration

    • Performance calibration allows you to test, fine-tune, and simulate running event detection models using continuous real-world or synthetically generated streams of data

    • Currently only available for audio data projects

v1.13.3

September 27, 2022

  • EON Tuner Search Space

    • Added validation for custom EON Tuner search space JSON

    • Added support for using custom organization DSP blocks in EON tuner search space

  • Show public project license

v1.9.8

September 15, 2022

  • Add label filter to DSP view

    • On the DSP block tab, select from a "Show labels" dropdown to quickly view the DSP processing results for a specific sample

v1.9.6

September 14, 2022

  • Edit Block Locally

    • Any built-in block in the Edge Impulse Studio can be edited locally, and then pushed back as a custom block

    • To download a block, go to any learning block in your project, click the three dots, select "Edit block locally", and follow the instructions in the README

v1.9.1

September 13, 2022

v1.9.0

September 9, 2022

  • New library deployment (beta): BrainChip (for image-based projects)

    • A MetaTF converted saved model (.fbz) for use with the Akida runtime

v1.7.5

September 5, 2022

  • Espressif ESP32

    • Added ESP-NN into the Edge Impulse SDK for ESP32 deployment

v1.7.0

August 31, 2022

v1.5.2

August 21, 2022

v1.5.0

August 17, 2022

v1.4.23

August 4, 2022

  • Spectral Analysis v2

    • Easier to use, with less DSP parameters needed for good performance

    • Generalizes better (that is, performs well with data it wasn't trained on)

    • Generally uses less RAM than v1

  • Raspberry Pi RP2040

    • Added continuous inference with FreeRTOS

    • Added mic support for RP2040 Connect

Last updated