Edge Impulse Experts / huggingface Public
Target: Nvidia Jetson Nano 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

Nvidia Jetson Nano

100 ms

4194304 kB

16777216 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

80%
rgb-mobilenetv2-b2f
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
938 kB of 4194304 kB
ROM
683 kB of 16777216 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

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

0.0005 | 20 | 80%

MobileNetV2 0.1
64 | 0.1 |

12/22/2022, 4:17:48 PM

78%
rgb-mobilenetv1-2d8
PERFORMANCE
LATENCY
5 ms of 100 ms
RAM
848 kB of 4194304 kB
ROM
923 kB of 16777216 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

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

0.0005 | 20 | 78%

MobileNetV1 0.25
64 | 0.1 |

12/22/2022, 4:14:27 PM

73%
rgb-mobilenetv2-ab5
PERFORMANCE
LATENCY
3 ms of 100 ms
RAM
938 kB of 4194304 kB
ROM
438 kB of 16777216 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

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

0.0005 | 20 | 73%

MobileNetV2 0.1
16 | 0.1

12/22/2022, 4:04:25 PM

71%
rgb-mobilenetv2-ab3
PERFORMANCE
LATENCY
5 ms of 100 ms
RAM
982 kB of 4194304 kB
ROM
2766 kB of 16777216 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

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

0.0005 | 20 | 71%

MobileNetV2 160x160 0.5
16 | 0.1

12/22/2022, 4:19:13 PM

66%
rgb-mobilenetv1-b4d
PERFORMANCE
LATENCY
1 ms of 100 ms
RAM
160 kB of 4194304 kB
ROM
206 kB of 16777216 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

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

0.0005 | 20 | 66%

MobileNetV1 0.1
64 | 0.1

12/22/2022, 4:10:23 PM

65%
rgb-conv2d-d25
PERFORMANCE
LATENCY
6 ms of 100 ms
RAM
89 kB of 4194304 kB
ROM
405 kB of 16777216 kB
DSP NN Unused
IMAGE INPUT

32 |
32

IMAGE

RGB

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 10 | 65%

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

12/22/2022, 4:06:24 PM

63%
rgb-mobilenetv1-465
PERFORMANCE
LATENCY
5 ms of 100 ms
RAM
641 kB of 4194304 kB
ROM
619 kB of 16777216 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

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

0.0005 | 20 | 63%

MobileNetV1 0.2
64 | 0.5 |

12/22/2022, 4:10:34 PM

58%
rgb-mobilenetv1-629
PERFORMANCE
LATENCY
1 ms of 100 ms
RAM
332 kB of 4194304 kB
ROM
874 kB of 16777216 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

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

0.0005 | 20 | 58%

MobileNetV1 0.25
16 | 0.5 |

12/22/2022, 4:03:28 PM

53%
rgb-conv2d-254
PERFORMANCE
LATENCY
8 ms of 100 ms
RAM
184 kB of 4194304 kB
ROM
126 kB of 16777216 kB
DSP NN Unused
IMAGE INPUT

64 |
64

IMAGE

RGB

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 10 | 53%

Type Filters Kernel Rate
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
dropout - - 0.25

12/22/2022, 4:01:06 PM

52%
rgb-mobilenetv2-380
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
938 kB of 4194304 kB
ROM
438 kB of 16777216 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

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

0.0005 | 20 | 52%

MobileNetV2 0.1
16 | 0.5 |

12/22/2022, 4:20:37 PM

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