Developer Marcial / PetDetect Public
Target: Arduino Portenta H7 (Cortex-M7 480MHz) Clone this project
Experiments EON Tuner
The EON Tuner helps you find the most optimal architecture for your embedded machine-learning application. Clone this project to use the EON Tuner.

Target

No name set

Arduino Portenta H7 (Cortex-M7 480MHz)

100 ms

1024 kB

2048 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

99%
rgb-mobilenetv1-5ca
Show logs
PERFORMANCE
LATENCY
157 ms of 100 ms
Exceeds target by 57 ms
RAM
264 kB of 1024 kB
ROM
324 kB of 2048 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

ACCURACY (KERAS-TRANSFER-IMAGE)
TRANSFER LEARNING (IMAGES)

0.0005 | 20 | 99%

MobileNetV1 0.25
64 | 0.1

8/4/2022, 1:30:00 AM

99%
rgb-mobilenetv1-6af
Show logs
PERFORMANCE
LATENCY
105 ms of 100 ms
Exceeds target by 5 ms
RAM
264 kB of 1024 kB
ROM
324 kB of 2048 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

ACCURACY (KERAS-TRANSFER-IMAGE)
TRANSFER LEARNING (IMAGES)

0.0005 | 20 | 99%

MobileNetV1 0.25
64 | 0.5

8/4/2022, 1:30:11 AM

99%
rgb-mobilenetv1-c7b
Show logs
PERFORMANCE
LATENCY
168 ms of 100 ms
Exceeds target by 68 ms
RAM
264 kB of 1024 kB
ROM
312 kB of 2048 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

ACCURACY (KERAS-TRANSFER-IMAGE)
TRANSFER LEARNING (IMAGES)

0.0005 | 20 | 99%

MobileNetV1 0.25
16 | 0.5 |

8/4/2022, 1:13:57 AM

98%
grayscale-mobilenetv1-feb
Show logs
PERFORMANCE
LATENCY
113 ms of 100 ms
Exceeds target by 13 ms
RAM
264 kB of 1024 kB
ROM
312 kB of 2048 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

Grayscale

ACCURACY (KERAS-TRANSFER-IMAGE)
TRANSFER LEARNING (IMAGES)

0.0005 | 20 | 98%

MobileNetV1 0.25
16 | 0.1 |

8/4/2022, 1:10:17 AM

96%
rgb-mobilenetv1-e5e
Show logs
PERFORMANCE
LATENCY
92 ms of 100 ms
RAM
207 kB of 1024 kB
ROM
228 kB of 2048 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

ACCURACY (KERAS-TRANSFER-IMAGE)
TRANSFER LEARNING (IMAGES)

0.0005 | 20 | 96%

MobileNetV1 0.2
16 | 0.5 |

8/4/2022, 1:11:51 AM

grayscale-conv2d-fd9
PERFORMANCE
LATENCY
100 ms
RAM
1024 kB
ROM
2048 kB
Unused
IMAGE INPUT

64 |
64

IMAGE

Grayscale

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.0005 | 10

Type Filters Kernel Rate
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
dropout - - 0.5

rgb-mobilenetv2-1ba
PERFORMANCE
LATENCY
100 ms
RAM
1024 kB
ROM
2048 kB
Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

ACCURACY (KERAS-TRANSFER-IMAGE)
TRANSFER LEARNING (IMAGES)

0.0005 | 20

MobileNetV2 0.35
64 | 0.1

rgb-mobilenetv2-13f
PERFORMANCE
LATENCY
100 ms
RAM
1024 kB
ROM
2048 kB
Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

ACCURACY (KERAS-TRANSFER-IMAGE)
TRANSFER LEARNING (IMAGES)

0.0005 | 20

MobileNetV2 0.05
16 | 0.5

grayscale-mobilenetv2-87c
PERFORMANCE
LATENCY
100 ms
RAM
1024 kB
ROM
2048 kB
Unused
IMAGE INPUT

96 |
96

IMAGE

Grayscale

ACCURACY (KERAS-TRANSFER-IMAGE)
TRANSFER LEARNING (IMAGES)

0.0005 | 20

MobileNetV2 0.35
16 | 0.1

grayscale-conv2d-9f0
PERFORMANCE
LATENCY
100 ms
RAM
1024 kB
ROM
2048 kB
Unused
IMAGE INPUT

32 |
32

IMAGE

Grayscale

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.0005 | 10

Type Filters Kernel Rate
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
dropout - - 0.25

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