MJRoBot (Marcelo Rovai) / UNO-Q Image Classification Public
Target: Arduino UNO Q (Qualcomm QRB2210) 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

Arduino UNO Q (Qualcomm QRB2210)

100 ms

2097152 kB

8388608 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

100%
rgb-mobilenetv2-057
PERFORMANCE
LATENCY
7 ms of 100 ms
RAM
285 kB of 2097152 kB
ROM
222 kB of 8388608 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

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

0.0005 | 20 | 100%

MobileNetV2 0.1
16 | 0.5

7/12/2024, 12:08:02 PM

100%
rgb-mobilenetv2-10d
PERFORMANCE
LATENCY
8 ms of 100 ms
RAM
275 kB of 2097152 kB
ROM
234 kB of 8388608 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

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

0.0005 | 20 | 100%

MobileNetV2 0.05
64 | 0.1

7/12/2024, 12:12:44 PM

100%
grayscale-mobilenetv2-39d
PERFORMANCE
LATENCY
5 ms of 100 ms
RAM
285 kB of 2097152 kB
ROM
284 kB of 8388608 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

Grayscale

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

0.0005 | 20 | 100%

MobileNetV2 0.1
64 | 0.5 |

7/12/2024, 12:12:47 PM

97%
grayscale-mobilenetv2-a2b
PERFORMANCE
LATENCY
12 ms of 100 ms
RAM
339 kB of 2097152 kB
ROM
585 kB of 8388608 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

Grayscale

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

0.0005 | 20 | 97%

MobileNetV2 0.35
16 | 0.1

7/12/2024, 12:17:18 PM

91%
rgb-mobilenetv1-4a4
PERFORMANCE
LATENCY
6 ms of 100 ms
RAM
123 kB of 2097152 kB
ROM
110 kB of 8388608 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

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

0.0005 | 20 | 91%

MobileNetV1 0.1
64 | 0.1

7/12/2024, 12:07:25 PM

91%
grayscale-mobilenetv2-399
PERFORMANCE
LATENCY
7 ms of 100 ms
RAM
275 kB of 2097152 kB
ROM
234 kB of 8388608 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

Grayscale

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

0.0005 | 20 | 91%

MobileNetV2 0.05
64 | 0.1 |

7/12/2024, 12:08:17 PM

91%
rgb-mobilenetv2-4e6
PERFORMANCE
LATENCY
16 ms of 100 ms
RAM
339 kB of 2097152 kB
ROM
647 kB of 8388608 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

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

0.0005 | 20 | 91%

MobileNetV2 0.35
64 | 0.5

7/12/2024, 12:08:21 PM

grayscale-conv2d-588
PERFORMANCE
LATENCY
9 ms of 100 ms
RAM
47 kB of 2097152 kB
ROM
43 kB of 8388608 kB
DSP NN Unused
IMAGE INPUT

64 |
64

IMAGE

Grayscale

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 10 | 0%

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

7/12/2024, 12:05:58 PM

77%
rgb-mobilenetv2-dd3
PERFORMANCE
LATENCY
13 ms of 100 ms
RAM
339 kB of 2097152 kB
ROM
585 kB of 8388608 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

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

0.0005 | 20 | 77%

MobileNetV2 0.35
16 | 0.1 |

7/12/2024, 12:12:45 PM

74%
grayscale-mobilenetv1-be7
PERFORMANCE
LATENCY
7 ms of 100 ms
RAM
129 kB of 2097152 kB
ROM
307 kB of 8388608 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

Grayscale

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

0.0005 | 20 | 74%

MobileNetV1 0.25
16 | 0.5 |

7/12/2024, 12:16:10 PM

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