Avi / micro_ros_ei 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

rgb-mobilenetv1-6b4
PERFORMANCE
LATENCY
328 ms of 100 ms
Exceeds target by 228 ms
RAM
208 kB of 340 kB
ROM
224 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

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

0.0005 | 20

MobileNetV1 0.2
16 | 0.5 |

9/10/2022, 8:43:54 AM

grayscale-mobilenetv2-d47
PERFORMANCE
LATENCY
70 ms of 100 ms
RAM
684 kB of 340 kB
Exceeds target by 344 kB
ROM
219 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

Grayscale

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

0.0005 | 20

MobileNetV2 0.1
16 | 0.1 |

9/10/2022, 8:44:46 AM

rgb-mobilenetv1-0b4
PERFORMANCE
LATENCY
592 ms of 100 ms
Exceeds target by 492 ms
RAM
135 kB of 340 kB
ROM
320 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

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

0.0005 | 20

MobileNetV1 0.25
64 | 0.5

9/10/2022, 8:44:00 AM

rgb-conv2d-864
PERFORMANCE
LATENCY
297 ms of 100 ms
Exceeds target by 197 ms
RAM
51 kB of 340 kB
ROM
36 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

64 |
64

IMAGE

RGB

ACCURACY (KERAS)
CLASSIFICATION (KERAS)

0.0005 | 10

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

9/10/2022, 8:45:13 AM

rgb-mobilenetv2-1ea
PERFORMANCE
LATENCY
637 ms of 100 ms
Exceeds target by 537 ms
RAM
674 kB of 340 kB
Exceeds target by 334 kB
ROM
231 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

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

0.0005 | 20

MobileNetV2 0.05
64 | 0.5 |

9/10/2022, 8:47:58 AM

grayscale-mobilenetv2-579
PERFORMANCE
LATENCY
45 ms of 100 ms
RAM
351 kB of 340 kB
Exceeds target by 11 kB
ROM
581 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

Grayscale

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

0.0005 | 20

MobileNetV2 0.35
16 | 0.5 |

9/10/2022, 8:48:18 AM

grayscale-mobilenetv1-9d4
PERFORMANCE
LATENCY
546 ms of 100 ms
Exceeds target by 446 ms
RAM
135 kB of 340 kB
ROM
320 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

Grayscale

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

0.0005 | 20

MobileNetV1 0.25
64 | 0.5

9/10/2022, 8:48:59 AM

rgb-mobilenetv2-7b8
PERFORMANCE
LATENCY
66 ms of 100 ms
RAM
674 kB of 340 kB
Exceeds target by 334 kB
ROM
169 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

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

0.0005 | 20

MobileNetV2 0.05
16 | 0.1

9/10/2022, 8:51:30 AM

rgb-mobilenetv1-6a5
PERFORMANCE
LATENCY
428 ms of 100 ms
Exceeds target by 328 ms
RAM
135 kB of 340 kB
ROM
320 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

96 |
96

IMAGE

RGB

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

0.0005 | 20

MobileNetV1 0.25
64 | 0.1

9/10/2022, 8:51:18 AM

rgb-mobilenetv2-bae
PERFORMANCE
LATENCY
66 ms of 100 ms
RAM
684 kB of 340 kB
Exceeds target by 344 kB
ROM
219 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

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

0.0005 | 20

MobileNetV2 0.1
16 | 0.5

9/10/2022, 8:53:53 AM

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