shugarry / Pothole and road safety detection Public
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

Run 1

Arduino UNO Q (Qualcomm QRB2210)

100 ms

4194304 kB

8388608 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

21%
grayscale-fomo-678
PERFORMANCE
LATENCY
14 ms of 100 ms
RAM
409 kB of 4194304 kB
ROM
58 kB of 8388608 kB
DSP NN Unused
IMAGE INPUT

128 |
128

IMAGE

Grayscale

OBJECT DETECTION (IMAGES)

0.01 | 60 | 21%

FOMO (MobileNetV2 0.1) | int8

0 5/9/2026, 11:26:33 PM

17%
grayscale-fomo-46e
PERFORMANCE
LATENCY
14 ms of 100 ms
RAM
409 kB of 4194304 kB
ROM
58 kB of 8388608 kB
DSP NN Unused
IMAGE INPUT

128 |
128

IMAGE

Grayscale

OBJECT DETECTION (IMAGES)

0.01 | 60 | 17%

FOMO (MobileNetV2 0.1) | int8

0 5/9/2026, 10:59:25 PM

16%
grayscale-fomo-8f0
PERFORMANCE
LATENCY
8 ms of 100 ms
RAM
240 kB of 4194304 kB
ROM
58 kB of 8388608 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

Grayscale

OBJECT DETECTION (IMAGES)

0.01 | 30 | 16%

FOMO (MobileNetV2 0.1) | int8

1 5/9/2026, 11:40:14 PM

14%
rgb-fomo-c60
PERFORMANCE
LATENCY
8 ms of 100 ms
RAM
240 kB of 4194304 kB
ROM
59 kB of 8388608 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

OBJECT DETECTION (IMAGES)

0.01 | 60 | 14%

FOMO (MobileNetV2 0.1) | int8

0 5/9/2026, 11:18:45 PM

10%
grayscale-fomo-44c
PERFORMANCE
LATENCY
8 ms of 100 ms
RAM
240 kB of 4194304 kB
ROM
58 kB of 8388608 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

Grayscale

OBJECT DETECTION (IMAGES)

0.1 | 30 | 10%

FOMO (MobileNetV2 0.1) | int8

0 5/9/2026, 10:47:21 PM

0%
rgb-fomo-6be
PERFORMANCE
LATENCY
221 ms of 100 ms
Exceeds target by 121 ms
RAM
631 kB of 4194304 kB
ROM
71 kB of 8388608 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

OBJECT DETECTION (IMAGES)

0.1 | 60 | 0%

FOMO (MobileNetV2 0.35) | int8

0 5/9/2026, 11:24:24 PM