Edge Impulse Experts / icicle-monitor Public
Target: Arduino Portenta H7 (Cortex-M7 480MHz) 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

No name set

Arduino Portenta H7 (Cortex-M7 480MHz)

100 ms

440 kB

2048 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

Run #1 (Apr 06 2024, 19:04:11, finished)
86%
grayscale-fomo-df3
PERFORMANCE
LATENCY
168 ms of 100 ms
Exceeds target by 68 ms
RAM
630 kB of 440 kB
Exceeds target by 190 kB
ROM
78 kB of 2048 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

Grayscale

OBJECT DETECTION (IMAGES)

0.01 | 60 | 86%

FOMO (MobileNetV2 0.35) | int8

4/7/2024, 2:22:48 AM

85%
grayscale-fomo-3a9
PERFORMANCE
LATENCY
123 ms of 100 ms
Exceeds target by 23 ms
RAM
627 kB of 440 kB
Exceeds target by 187 kB
ROM
64 kB of 2048 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

Grayscale

OBJECT DETECTION (IMAGES)

0.01 | 30 | 85%

FOMO (MobileNetV2 0.1) | int8

4/6/2024, 10:37:40 PM

84%
rgb-fomo-7fa
PERFORMANCE
LATENCY
111 ms of 100 ms
Exceeds target by 11 ms
RAM
627 kB of 440 kB
Exceeds target by 187 kB
ROM
64 kB of 2048 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

OBJECT DETECTION (IMAGES)

0.01 | 30 | 84%

FOMO (MobileNetV2 0.1) | int8

4/7/2024, 2:41:11 AM

78%
rgb-fomo-591
PERFORMANCE
LATENCY
54 ms of 100 ms
RAM
243 kB of 440 kB
ROM
78 kB of 2048 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

OBJECT DETECTION (IMAGES)

0.01 | 30 | 78%

FOMO (MobileNetV2 0.35) | int8

4/7/2024, 6:57:40 AM

78%
grayscale-fomo-92e
PERFORMANCE
LATENCY
64 ms of 100 ms
RAM
243 kB of 440 kB
ROM
78 kB of 2048 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

Grayscale

OBJECT DETECTION (IMAGES)

0.01 | 60 | 78%

FOMO (MobileNetV2 0.35) | int8

4/7/2024, 6:54:32 AM

78%
grayscale-fomo-506
PERFORMANCE
LATENCY
76 ms of 100 ms
RAM
409 kB of 440 kB
ROM
64 kB of 2048 kB
DSP NN Unused
IMAGE INPUT

128 |
128

IMAGE

Grayscale

OBJECT DETECTION (IMAGES)

0.01 | 30 | 78%

FOMO (MobileNetV2 0.1) | int8

4/6/2024, 9:26:10 PM

77%
rgb-fomo-43c
PERFORMANCE
LATENCY
45 ms of 100 ms
RAM
240 kB of 440 kB
ROM
64 kB of 2048 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

OBJECT DETECTION (IMAGES)

0.01 | 30 | 77%

FOMO (MobileNetV2 0.1) | int8

4/7/2024, 1:08:32 AM

75%
rgb-fomo-954
PERFORMANCE
LATENCY
126 ms of 100 ms
Exceeds target by 26 ms
RAM
627 kB of 440 kB
Exceeds target by 187 kB
ROM
64 kB of 2048 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

OBJECT DETECTION (IMAGES)

0.1 | 60 | 75%

FOMO (MobileNetV2 0.1) | int8

4/7/2024, 7:57:32 AM

75%
rgb-fomo-9db
PERFORMANCE
LATENCY
80 ms of 100 ms
RAM
409 kB of 440 kB
ROM
64 kB of 2048 kB
DSP NN Unused
IMAGE INPUT

128 |
128

IMAGE

RGB

OBJECT DETECTION (IMAGES)

0.1 | 60 | 75%

FOMO (MobileNetV2 0.1) | int8

4/7/2024, 7:05:57 AM

68%
rgb-fomo-0c0
PERFORMANCE
LATENCY
67 ms of 100 ms
RAM
243 kB of 440 kB
ROM
78 kB of 2048 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

OBJECT DETECTION (IMAGES)

0.1 | 30 | 68%

FOMO (MobileNetV2 0.35) | int8

4/7/2024, 7:00:42 AM

Help & documentation Get help on the forum Send feedback Contact sales
Join us
Terms of Service Privacy policy