mtxslv / cats_and_dogs_breeds Public
Target: Arduino Nano 33 BLE Sense (Cortex-M4F 64MHz) Clone this project
Impulses 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 Nano 33 BLE Sense (Cortex-M4F 64MHz)

100 ms

256 kB

1024 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

83%
rgb-mobilenetv2-84a
Show logs
PERFORMANCE
LATENCY
2015 ms of 100 ms
Exceeds target by 1915 ms
RAM
351 kB of 256 kB
Exceeds target by 95 kB
ROM
645 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

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

0.0005 | 20 | 83%

MobileNetV2 0.35
64 | 0.5

12/10/2022, 1:01:24 AM

83%
rgb-mobilenetv2-1c3
Show logs
PERFORMANCE
LATENCY
1991 ms of 100 ms
Exceeds target by 1891 ms
RAM
351 kB of 256 kB
Exceeds target by 95 kB
ROM
645 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

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

0.0005 | 20 | 83%

MobileNetV2 160x160 0.35
64 | 0.5

12/10/2022, 1:07:32 AM

82%
rgb-mobilenetv2-da1
Show logs
PERFORMANCE
LATENCY
1976 ms of 100 ms
Exceeds target by 1876 ms
RAM
351 kB of 256 kB
Exceeds target by 95 kB
ROM
645 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

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

0.0005 | 20 | 82%

MobileNetV2 0.35
64 | 0.1 |

12/10/2022, 1:13:42 AM

77%
rgb-mobilenetv1-9a1
Show logs
PERFORMANCE
LATENCY
1189 ms of 100 ms
Exceeds target by 1089 ms
RAM
135 kB of 256 kB
ROM
324 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

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

0.0005 | 20 | 77%

MobileNetV1 0.25
64 | 0.1 |

12/10/2022, 1:05:46 AM

61%
rgb-mobilenetv2-92f
Show logs
PERFORMANCE
LATENCY
2490 ms of 100 ms
Exceeds target by 2390 ms
RAM
674 kB of 256 kB
Exceeds target by 418 kB
ROM
171 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

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

0.0005 | 20 | 61%

MobileNetV2 0.05
16 | 0.1 |

12/10/2022, 1:06:16 AM

55%
rgb-mobilenetv1-c81
Show logs
PERFORMANCE
LATENCY
1196 ms of 100 ms
Exceeds target by 1096 ms
RAM
135 kB of 256 kB
ROM
312 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

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

0.0005 | 20 | 55%

MobileNetV1 0.25
16 | 0.5 |

12/10/2022, 12:57:23 AM

44%
rgb-mobilenetv1-21e
Show logs
PERFORMANCE
LATENCY
2200 ms of 100 ms
Exceeds target by 2100 ms
RAM
208 kB of 256 kB
ROM
238 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

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

0.0005 | 20 | 44%

MobileNetV1 0.2
64 | 0.5 |

12/10/2022, 1:12:21 AM

44%
rgb-mobilenetv1-c27
Show logs
PERFORMANCE
LATENCY
2200 ms of 100 ms
Exceeds target by 2100 ms
RAM
208 kB of 256 kB
ROM
238 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

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

0.0005 | 20 | 44%

MobileNetV1 0.2
64 | 0.5 |

12/10/2022, 1:00:27 AM

23%
rgb-mobilenetv2-26a
Show logs
PERFORMANCE
LATENCY
2688 ms of 100 ms
Exceeds target by 2588 ms
RAM
684 kB of 256 kB
Exceeds target by 428 kB
ROM
221 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

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

0.0005 | 20 | 23%

MobileNetV2 0.1
16 | 0.5

12/10/2022, 1:15:19 AM

14%
rgb-conv2d-9ff
Show logs
PERFORMANCE
LATENCY
485 ms of 100 ms
Exceeds target by 385 ms
RAM
34 kB of 256 kB
ROM
129 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

32 |
32

IMAGE

RGB

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 10 | 14%

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

12/10/2022, 12:55:19 AM

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