Dashboard
Data acquisition
Experiments
- EON Tuner
Impulse design
Impulse #1

Getting started

Documentation
Forums
Discord

Ankita Jadhav / lab_human_detection Public

Clone this project

Ankita Jadhav / lab_human_detection Public

Target: Espressif ESP-EYE (ESP32 240MHz) Clone this project

Experiments EON Tuner

The EON Tuner helps you quickly run hyper-parameter sweeps that explore different pre-processing + model architectures optimized for your defined objectives. Clone this project to use the EON Tuner.

Target

test5

Espressif ESP-EYE (ESP32 240MHz)

100 ms

4096 kB

4096 kB

Filters

Status

Pending 0

Running 0

Completed 10

Failed 0

DSP type

Grayscale 3

RGB 7

Model type

FOMO 10

View

Data set

Validation

Test

Variant

Sort

General

Accuracy

Latency

RAM

ROM

Last updated

F1-score

Precision

Recall

Run #13 - test5 (Mar 22 2024, 09:47:12, finished)

Run #17 - tuner (Apr 09 2024, 13:44:50, finished) Run #16 - test6 (Apr 07 2024, 13:20:36, finished) Run #15 - test5 (Mar 31 2024, 16:06:50, running) Run #14 - test5 (Mar 22 2024, 16:43:18, finished) Run #13 - test5 (Mar 22 2024, 09:47:12, finished) Run #12 - test5 (Mar 22 2024, 09:25:33, cancelled) Run #11 - test4 (Mar 21 2024, 20:56:09, finished) Run #10 - test4 (Mar 19 2024, 17:15:35, finished) Run #9 - test4 (Mar 19 2024, 16:07:32, finished) Run #8 - test4 (Mar 18 2024, 12:59:55, cancelled) Run #7 - test4 (Mar 18 2024, 12:34:19, cancelled) Run #6 - test3 (Mar 18 2024, 12:03:21, cancelled) Run #5 - test3 (Mar 17 2024, 21:26:12, finished) Run #4 - test2 (Mar 15 2024, 12:46:49, finished) Run #3 - test1 (Mar 14 2024, 18:26:52, finished) Run #2 - test1 (Mar 14 2024, 18:21:03, finished) Run #1 - testing (Mar 14 2024, 13:05:13, finished)

89%

grayscale-fomo-3e3

PERFORMANCE

LATENCY

1011 ms of 100 ms

Exceeds target by 911 ms

RAM

240 kB of 4096 kB

ROM

64 kB of 4096 kB

DSP NN Unused

IMAGE INPUT

96 |

96

IMAGE

Grayscale

OBJECT DETECTION (IMAGES)

0.01 | 30 | 89%

FOMO (MobileNetV2 0.1) | int8

3/22/2024, 9:55:54 AM

83%

grayscale-fomo-ad5

PERFORMANCE

LATENCY

1038 ms of 100 ms

Exceeds target by 938 ms

RAM

240 kB of 4096 kB

ROM

64 kB of 4096 kB

DSP NN Unused

IMAGE INPUT

96 |

96

IMAGE

Grayscale

OBJECT DETECTION (IMAGES)

0.1 | 60 | 83%

FOMO (MobileNetV2 0.1) | int8

3/22/2024, 10:08:08 AM

80%

rgb-fomo-d17

PERFORMANCE

LATENCY

1076 ms of 100 ms

Exceeds target by 976 ms

RAM

240 kB of 4096 kB

ROM

64 kB of 4096 kB

DSP NN Unused

IMAGE INPUT

96 |

96

IMAGE

RGB

OBJECT DETECTION (IMAGES)

0.01 | 30 | 80%

FOMO (MobileNetV2 0.1) | int8

3/22/2024, 10:29:27 AM

80%

rgb-fomo-764

PERFORMANCE

LATENCY

1066 ms of 100 ms

Exceeds target by 966 ms

RAM

240 kB of 4096 kB

ROM

64 kB of 4096 kB

DSP NN Unused

IMAGE INPUT

96 |

96

IMAGE

RGB

OBJECT DETECTION (IMAGES)

0.01 | 60 | 80%

FOMO (MobileNetV2 0.1) | int8

3/22/2024, 9:58:28 AM

79%

rgb-fomo-96c

PERFORMANCE

LATENCY

1485 ms of 100 ms

Exceeds target by 1385 ms

RAM

243 kB of 4096 kB

ROM

79 kB of 4096 kB

DSP NN Unused

IMAGE INPUT

96 |

96

IMAGE

RGB

OBJECT DETECTION (IMAGES)

0.01 | 30 | 79%

FOMO (MobileNetV2 0.35) | int8

3/22/2024, 10:16:16 AM

79%

rgb-fomo-6bd

PERFORMANCE

LATENCY

1154 ms of 100 ms

Exceeds target by 1054 ms

RAM

240 kB of 4096 kB

ROM

64 kB of 4096 kB

DSP NN Unused

IMAGE INPUT

96 |

96

IMAGE

RGB

OBJECT DETECTION (IMAGES)

0.1 | 60 | 79%

FOMO (MobileNetV2 0.1) | int8

3/22/2024, 10:10:01 AM

76%

grayscale-fomo-5f4

PERFORMANCE

LATENCY

1010 ms of 100 ms

Exceeds target by 910 ms

RAM

240 kB of 4096 kB

ROM

64 kB of 4096 kB

DSP NN Unused

IMAGE INPUT

96 |

96

IMAGE

Grayscale

OBJECT DETECTION (IMAGES)

0.1 | 30 | 76%

FOMO (MobileNetV2 0.1) | int8

3/22/2024, 10:00:18 AM

76%

rgb-fomo-a06

PERFORMANCE

LATENCY

1444 ms of 100 ms

Exceeds target by 1344 ms

RAM

243 kB of 4096 kB

ROM

78 kB of 4096 kB

DSP NN Unused

IMAGE INPUT

96 |

96

IMAGE

RGB

OBJECT DETECTION (IMAGES)

0.1 | 30 | 76%

FOMO (MobileNetV2 0.35) | int8

3/22/2024, 10:22:18 AM

75%

rgb-fomo-e0c

PERFORMANCE

LATENCY

1058 ms of 100 ms

Exceeds target by 958 ms

RAM

240 kB of 4096 kB

ROM

64 kB of 4096 kB

DSP NN Unused

IMAGE INPUT

96 |

96

IMAGE

RGB

OBJECT DETECTION (IMAGES)

0.1 | 60 | 75%

FOMO (MobileNetV2 0.1) | int8

3/22/2024, 10:23:58 AM

75%

rgb-fomo-691

PERFORMANCE

LATENCY

1050 ms of 100 ms

Exceeds target by 950 ms

RAM

240 kB of 4096 kB

ROM

64 kB of 4096 kB

DSP NN Unused

IMAGE INPUT

96 |

96

IMAGE

RGB

OBJECT DETECTION (IMAGES)

0.1 | 30 | 75%

FOMO (MobileNetV2 0.1) | int8

3/22/2024, 10:15:34 AM

Training output

Hide

Click 'Run EON Tuner' to begin

Configure a new EON Tuner run

The EON Tuner uses a Bayesian search algorithm to find optimal impulse configurations. To get started, select at least one run objective and configure your search space.

Name

Compute limit

Run objectives

Search space configuration

USE CASE

TUNER CONFIGURATION

Run #17 - tuner (Apr 09), finished Run #16 - test6 (Apr 07), finished Run #15 - test5 (Mar 31), running Run #14 - test5 (Mar 22), finished Run #13 - test5 (Mar 22), finished Run #12 - test5 (Mar 22), cancelled Run #11 - test4 (Mar 21), finished Run #10 - test4 (Mar 19), finished Run #9 - test4 (Mar 19), finished Run #8 - test4 (Mar 18), cancelled Run #7 - test4 (Mar 18), cancelled Run #6 - test3 (Mar 18), cancelled Run #5 - test3 (Mar 17), finished Run #4 - test2 (Mar 15), finished Run #3 - test1 (Mar 14), finished Run #2 - test1 (Mar 14), finished Run #1 - testing (Mar 14), finished

IMPULSE CONFIGURATION

Impulse #1

INPUT

Time-series
Pre-processed features

DSP

Raw
Spectral analysis
IMU (Syntiant)

LEARN

Dense
Convolutional (1D)

ANOMALY

Anomaly (k-means)
Anomaly (GMM)

ORGANIZATION (DSP)

Add custom DSP block
Add custom ML block

Custom search space

Do more with EON Tuner

Access more parallel EON Tuner jobs for faster results, a fully customizable search space, and more model variant options.

© 2025 EdgeImpulse Inc. All rights reserved

Show logs

Waiting...

Cancel job

Help & documentation Get help on the forum Send feedback Contact sales

Join us

Terms of Service Privacy policy

Send us your feedback!

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

Sign up to clone this project

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

Sign up for free

I already have an account

Configure your target device and application budget

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 type

Processor family

Processor architecture

Clock rate

| MHz

Max

Accelerator

Device ID (optional)

Custom device name (optional)

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

Choose your pricing

YEARLY

$400 /month

billed annually

SAVE 15%

MONTHLY

$475 /month

billed monthly

Additional usage

Professional Plan includes 1,000 compute minutes per month. Additional usage will be charged at $0.10 per minute, billed monthly.

Upgrade to Enterprise

Why is this the right time for your team to invest in edge AI? What best describes your use case? What is your expected timeline for solving your problem?