Developer Relations / Microscope - VeLO Public
Clone this project

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

Vision

Renesas RA6M5 (Cortex-M33 200MHz)

100 ms

80 kB

2048 kB

Filters

Status

DSP type

Network type

View

Data set

Precision

Sort

General

F1-score

Precision

Recall

75%
rgb-conv2d-304
Show logs
PERFORMANCE
LATENCY
119 ms of 100 ms
Exceeds target by 19 ms
RAM
50 kB of 512 kB
ROM
46 kB of 2048 kB
DSP NN Unused
INPUT

64 | 64

IMAGE

RGB

ACCURACY
CLASSIFICATION

0.0005 | 10

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

4/18/2023, 1:26:04 PM

69%
rgb-mobilenetv1-f8d
Show logs
PERFORMANCE
LATENCY
60 ms of 100 ms
RAM
64 kB of 512 kB
ROM
114 kB of 2048 kB
DSP NN Unused
INPUT

96 | 96

IMAGE

RGB

ACCURACY
TRANSFER LEARNING (IMAGES)

0.0005 | 20

MobileNetV1 0.1
64 | 0.5 |

4/18/2023, 1:28:05 PM

63%
rgb-conv2d-a92
Show logs
PERFORMANCE
LATENCY
85 ms of 100 ms
RAM
27 kB of 512 kB
ROM
40 kB of 2048 kB
DSP NN Unused
INPUT

32 | 32

IMAGE

RGB

ACCURACY
CLASSIFICATION

0.0005 | 10

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

4/18/2023, 1:25:53 PM

53%
grayscale-mobilenetv1-5a0
Show logs
PERFORMANCE
LATENCY
55 ms of 100 ms
RAM
58 kB of 512 kB
ROM
114 kB of 2048 kB
DSP NN Unused
INPUT

96 | 96

IMAGE

Grayscale

ACCURACY
TRANSFER LEARNING (IMAGES)

0.0005 | 20

MobileNetV1 0.1
64 | 0.5 |

4/18/2023, 1:25:51 PM

53%
rgb-conv2d-298
Show logs
PERFORMANCE
LATENCY
46 ms of 100 ms
RAM
18 kB of 512 kB
ROM
34 kB of 2048 kB
DSP NN Unused
INPUT

32 | 32

IMAGE

RGB

ACCURACY
CLASSIFICATION

0.0005 | 10

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

4/18/2023, 1:25:46 PM

44%
rgb-mobilenetv1-871
Show logs
PERFORMANCE
LATENCY
60 ms of 100 ms
RAM
64 kB of 512 kB
ROM
114 kB of 2048 kB
DSP NN Unused
INPUT

96 | 96

IMAGE

RGB

ACCURACY
TRANSFER LEARNING (IMAGES)

0.0005 | 20

MobileNetV1 0.1
64 | 0.5

4/18/2023, 1:25:58 PM

38%
grayscale-conv2d-322
Show logs
PERFORMANCE
LATENCY
52 ms of 100 ms
RAM
19 kB of 512 kB
ROM
52 kB of 2048 kB
DSP NN Unused
INPUT

32 | 32

IMAGE

Grayscale

ACCURACY
CLASSIFICATION

0.0005 | 10

Type Filters Kernel Rate
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
dropout - - 0.5

4/18/2023, 1:24:57 PM

38%
rgb-mobilenetv1-5a6
Show logs
PERFORMANCE
LATENCY
60 ms of 100 ms
RAM
64 kB of 512 kB
ROM
109 kB of 2048 kB
DSP NN Unused
INPUT

96 | 96

IMAGE

RGB

ACCURACY
TRANSFER LEARNING (IMAGES)

0.0005 | 20

MobileNetV1 0.1
16 | 0.5

4/18/2023, 1:26:03 PM

28%
rgb-mobilenetv1-8bf
Show logs
PERFORMANCE
LATENCY
60 ms of 100 ms
RAM
64 kB of 512 kB
ROM
109 kB of 2048 kB
DSP NN Unused
INPUT

96 | 96

IMAGE

RGB

ACCURACY
TRANSFER LEARNING (IMAGES)

0.0005 | 20

MobileNetV1 0.1
16 | 0.5 |

4/18/2023, 1:28:15 PM

25%
rgb-mobilenetv1-8cb
Show logs
PERFORMANCE
LATENCY
60 ms of 100 ms
RAM
64 kB of 512 kB
ROM
109 kB of 2048 kB
DSP NN Unused
INPUT

96 | 96

IMAGE

RGB

ACCURACY
TRANSFER LEARNING (IMAGES)

0.0005 | 20

MobileNetV1 0.1
16 | 0.1

4/18/2023, 1:30:17 PM

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