AI at the Edge / Use Case: Wildlife Monitoring Public
Target: Cortex-M7 216MHz 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

Cortex-M7 216MHz

100 ms

340 kB

1024 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

90%
rgb-mobilenetv1-744
PERFORMANCE
LATENCY
67 ms of 100 ms
RAM
265 kB of 340 kB
ROM
354 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

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

0.0005 | 20 | 90%

MobileNetV1 0.25
64 | 0.1 |

10/4/2022, 6:55:26 PM

89%
rgb-mobilenetv1-425
PERFORMANCE
LATENCY
471 ms of 100 ms
Exceeds target by 371 ms
RAM
265 kB of 340 kB
ROM
342 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

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

0.0005 | 20 | 89%

MobileNetV1 0.25
16 | 0.5

10/4/2022, 7:09:51 PM

86%
rgb-mobilenetv2-1d5
PERFORMANCE
LATENCY
319 ms of 100 ms
Exceeds target by 219 ms
RAM
351 kB of 340 kB
Exceeds target by 11 kB
ROM
674 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

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

0.0005 | 20 | 86%

MobileNetV2 160x160 0.35
64 | 0.5

10/4/2022, 7:00:43 PM

86%
rgb-mobilenetv2-8b4
PERFORMANCE
LATENCY
314 ms of 100 ms
Exceeds target by 214 ms
RAM
351 kB of 340 kB
Exceeds target by 11 kB
ROM
674 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

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

0.0005 | 20 | 86%

MobileNetV2 0.35
64 | 0.5

10/4/2022, 6:59:17 PM

86%
rgb-mobilenetv2-ff7
PERFORMANCE
LATENCY
730 ms of 100 ms
Exceeds target by 630 ms
RAM
387 kB of 340 kB
Exceeds target by 47 kB
ROM
936 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

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

0.0005 | 20 | 86%

MobileNetV2 160x160 0.5
16 | 0.1

10/4/2022, 6:52:20 PM

85%
grayscale-mobilenetv1-9af
PERFORMANCE
LATENCY
85 ms of 100 ms
RAM
265 kB of 340 kB
ROM
354 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

Grayscale

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

0.0005 | 20 | 85%

MobileNetV1 0.25
64 | 0.1

10/4/2022, 7:02:24 PM

82%
rgb-mobilenetv2-9f4
PERFORMANCE
LATENCY
65 ms of 100 ms
RAM
675 kB of 340 kB
Exceeds target by 335 kB
ROM
200 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

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

0.0005 | 20 | 82%

MobileNetV2 0.05
16 | 0.1 |

10/4/2022, 7:09:52 PM

82%
rgb-mobilenetv1-94f
PERFORMANCE
LATENCY
509 ms of 100 ms
Exceeds target by 409 ms
RAM
208 kB of 340 kB
ROM
269 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

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

0.0005 | 20 | 82%

MobileNetV1 0.2
64 | 0.5 |

10/4/2022, 6:53:34 PM

82%
rgb-mobilenetv1-07b
PERFORMANCE
LATENCY
509 ms of 100 ms
Exceeds target by 409 ms
RAM
208 kB of 340 kB
ROM
269 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

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

0.0005 | 20 | 82%

MobileNetV1 0.2
64 | 0.5 |

10/4/2022, 7:07:54 PM

73%
rgb-conv2d-7d0
PERFORMANCE
LATENCY
17 ms of 100 ms
RAM
34 kB of 340 kB
ROM
159 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

32 |
32

IMAGE

RGB

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.0005 | 10 | 73%

Type Filters Kernel Rate
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
conv2d 128 3 -
dropout - - 0.25

10/4/2022, 6:47:49 PM

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