Student / Sorting 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

160x160, trainingBG

Espressif ESP-EYE (ESP32 240MHz)

100 ms

4096 kB

4096 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

Run #5 - 160x160, trainingBG (Feb 25 2024, 11:35:06, finished) Run #4 - No Squash, 96x96 (Feb 24 2024, 19:52:18, finished) Run #3 - Squash, 96x96 (Feb 24 2024, 19:35:33, finished) Run #2 (Feb 24 2024, 16:23:42, finished) Run #1 (Feb 24 2024, 11:17:18, finished)
90%
grayscale-fomo-534
PERFORMANCE
LATENCY
3792 ms of 100 ms
Exceeds target by 3692 ms
RAM
630 kB of 4096 kB
ROM
78 kB of 4096 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

Grayscale

OBJECT DETECTION (IMAGES)

0.01 | 60 | 90%

FOMO (MobileNetV2 0.35) | int8

2/25/2024, 11:56:07 AM

90%
grayscale-fomo-e5b
PERFORMANCE
LATENCY
3011 ms of 100 ms
Exceeds target by 2911 ms
RAM
627 kB of 4096 kB
ROM
64 kB of 4096 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

Grayscale

OBJECT DETECTION (IMAGES)

0.01 | 30 | 90%

FOMO (MobileNetV2 0.1) | int8

2/25/2024, 11:53:29 AM

70%
rgb-fomo-2a5
PERFORMANCE
LATENCY
1662 ms of 100 ms
Exceeds target by 1562 ms
RAM
244 kB of 4096 kB
ROM
78 kB of 4096 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

OBJECT DETECTION (IMAGES)

0.01 | 30 | 70%

FOMO (MobileNetV2 0.35) | int8

2/25/2024, 11:52:39 AM

70%
grayscale-fomo-aa3
PERFORMANCE
LATENCY
1450 ms of 100 ms
Exceeds target by 1350 ms
RAM
409 kB of 4096 kB
ROM
64 kB of 4096 kB
DSP NN Unused
IMAGE INPUT

128 |
128

IMAGE

Grayscale

OBJECT DETECTION (IMAGES)

0.01 | 30 | 70%

FOMO (MobileNetV2 0.1) | int8

2/25/2024, 11:56:24 AM

70%
grayscale-fomo-06d
PERFORMANCE
LATENCY
1439 ms of 100 ms
Exceeds target by 1339 ms
RAM
243 kB of 4096 kB
ROM
78 kB of 4096 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

Grayscale

OBJECT DETECTION (IMAGES)

0.01 | 60 | 70%

FOMO (MobileNetV2 0.35) | int8

2/25/2024, 11:48:26 AM

70%
rgb-fomo-0ed
PERFORMANCE
LATENCY
984 ms of 100 ms
Exceeds target by 884 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 | 70%

FOMO (MobileNetV2 0.1) | int8

2/25/2024, 11:49:07 AM

70%
rgb-fomo-bb0
PERFORMANCE
LATENCY
1161 ms of 100 ms
Exceeds target by 1061 ms
RAM
409 kB of 4096 kB
ROM
64 kB of 4096 kB
DSP NN Unused
IMAGE INPUT

128 |
128

IMAGE

RGB

OBJECT DETECTION (IMAGES)

0.1 | 60 | 70%

FOMO (MobileNetV2 0.1) | int8

2/25/2024, 11:49:46 AM

50%
rgb-fomo-a1d
PERFORMANCE
LATENCY
2545 ms of 100 ms
Exceeds target by 2445 ms
RAM
627 kB of 4096 kB
ROM
64 kB of 4096 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

OBJECT DETECTION (IMAGES)

0.1 | 60 | 50%

FOMO (MobileNetV2 0.1) | int8

2/25/2024, 11:47:33 AM

30%
rgb-fomo-e31
PERFORMANCE
LATENCY
3221 ms of 100 ms
Exceeds target by 3121 ms
RAM
627 kB of 4096 kB
ROM
64 kB of 4096 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

OBJECT DETECTION (IMAGES)

0.01 | 30 | 30%

FOMO (MobileNetV2 0.1) | int8

2/25/2024, 11:49:09 AM

20%
rgb-fomo-69d
PERFORMANCE
LATENCY
1487 ms of 100 ms
Exceeds target by 1387 ms
RAM
244 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 | 20%

FOMO (MobileNetV2 0.35) | int8

2/25/2024, 11:56:01 AM

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