Rob / stage 2 classify speed limit Public
Target: Raspberry Pi 4 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

Raspberry Pi 4

100 ms

8388608 kB

33554432 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

92%
rgb-mobilenetv2-9ad
PERFORMANCE
LATENCY
15 ms of 100 ms
RAM
738 kB of 8388608 kB
ROM
649 kB of 33554432 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

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

0.0005 | 20 | 92%

MobileNetV2 0.35
64 | 0.1

5/19/2022, 7:27:14 PM

88%
rgb-mobilenetv2-bdd
PERFORMANCE
LATENCY
14 ms of 100 ms
RAM
738 kB of 8388608 kB
ROM
586 kB of 33554432 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

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

0.0005 | 20 | 88%

MobileNetV2 0.35
16 | 0.1 |

5/19/2022, 7:27:29 PM

84%
rgb-mobilenetv2-3f2
PERFORMANCE
LATENCY
11 ms of 100 ms
RAM
738 kB of 8388608 kB
ROM
586 kB of 33554432 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

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

0.0005 | 20 | 84%

MobileNetV2 160x160 0.35
16 | 0.5

5/19/2022, 7:31:38 PM

80%
rgb-mobilenetv1-0fe
PERFORMANCE
LATENCY
7 ms of 100 ms
RAM
264 kB of 8388608 kB
ROM
324 kB of 33554432 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

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

0.0005 | 20 | 80%

MobileNetV1 0.25
64 | 0.1 |

5/19/2022, 7:31:45 PM

76%
rgb-mobilenetv2-d5b
PERFORMANCE
LATENCY
19 ms of 100 ms
RAM
670 kB of 8388608 kB
ROM
1633 kB of 33554432 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

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

0.0005 | 20 | 76%

MobileNetV2 160x160 0.75
16 | 0.5

5/19/2022, 7:28:11 PM

72%
rgb-mobilenetv1-8da
PERFORMANCE
LATENCY
6 ms of 100 ms
RAM
264 kB of 8388608 kB
ROM
324 kB of 33554432 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

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

0.0005 | 20 | 72%

MobileNetV1 0.25
64 | 0.5

5/19/2022, 7:33:01 PM

52%
grayscale-mobilenetv1-7de
PERFORMANCE
LATENCY
8 ms of 100 ms
RAM
264 kB of 8388608 kB
ROM
312 kB of 33554432 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

Grayscale

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

0.0005 | 20 | 52%

MobileNetV1 0.25
16 | 0.1 |

5/19/2022, 7:29:51 PM

36%
grayscale-mobilenetv1-528
PERFORMANCE
LATENCY
7 ms of 100 ms
RAM
264 kB of 8388608 kB
ROM
312 kB of 33554432 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

Grayscale

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

0.0005 | 20 | 36%

MobileNetV1 0.25
16 | 0.5

5/19/2022, 7:29:28 PM

12%
rgb-conv2d-f34
PERFORMANCE
LATENCY
59 ms of 100 ms
RAM
51 kB of 8388608 kB
ROM
42 kB of 33554432 kB
DSP NN Unused
IMAGE INPUT

64 |
64

IMAGE

RGB

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.0005 | 10 | 12%

Type Filters Kernel Rate
conv2d 8 3 -
conv2d 16 3 -
dropout - - 0.25

5/19/2022, 7:24:41 PM

grayscale-conv2d-187
PERFORMANCE
LATENCY
49 ms of 100 ms
RAM
30 kB of 8388608 kB
ROM
59 kB of 33554432 kB
DSP NN Unused
IMAGE INPUT

32 |
32

IMAGE

Grayscale

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.0005 | 10 | 0%

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

5/19/2022, 7:30:45 PM

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