Thomas Vikström / Alphabet 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

Motion events

Nordic nRF52840 DK (Cortex-M4F 64MHz)

150 ms

256 kB

1024 kB

Filters

Status

DSP type

Network type

View

Data set

Precision

Sort

General

F1-score

Precision

Recall

79%
spectr-dense-577
Show logs
PERFORMANCE
LATENCY
6 ms of 150 ms
RAM
25 kB of 256 kB
ROM
25 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 250 ms

SPECTRAL-ANALYSIS

1024

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

Type Filters Kernel Rate
dense 80 - -
dense 40 - -
dense 20 - -

1/26/2022, 3:23:37 PM

74%
spectr-dense-71f
Show logs
PERFORMANCE
LATENCY
6 ms of 150 ms
RAM
25 kB of 256 kB
ROM
25 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

SPECTRAL-ANALYSIS

1024

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

Type Filters Kernel Rate
dense 80 - -
dense 40 - -

1/26/2022, 3:15:11 PM

74%
spectr-dense-97e
Show logs
PERFORMANCE
LATENCY
4 ms of 150 ms
RAM
25 kB of 256 kB
ROM
22 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

SPECTRAL-ANALYSIS

1024

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

Type Filters Kernel Rate
dense 80 - -
dropout - - 0.25
dense 40 - -
dropout - - 0.25

1/26/2022, 3:22:30 PM

74%
spectr-dense-4b6
Show logs
PERFORMANCE
LATENCY
6 ms of 150 ms
RAM
25 kB of 256 kB
ROM
22 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

SPECTRAL-ANALYSIS

1024

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

Type Filters Kernel Rate
dense 80 - -
dropout - - 0.25
dense 40 - -
dropout - - 0.25

1/26/2022, 3:22:32 PM

71%
spectr-dense-b71
Show logs
PERFORMANCE
LATENCY
4 ms of 150 ms
RAM
25 kB of 256 kB
ROM
21 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

SPECTRAL-ANALYSIS

1024

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

Type Filters Kernel Rate
dense 40 - -
dense 20 - -

1/26/2022, 3:19:14 PM

71%
spectr-dense-877
Show logs
PERFORMANCE
LATENCY
2 ms of 150 ms
RAM
25 kB of 256 kB
ROM
21 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 250 ms

SPECTRAL-ANALYSIS

1024

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

Type Filters Kernel Rate
dense 40 - -
dense 20 - -

1/26/2022, 3:24:11 PM

69%
spectr-dense-ef9
Show logs
PERFORMANCE
LATENCY
2 ms of 150 ms
RAM
26 kB of 256 kB
ROM
21 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

SPECTRAL-ANALYSIS

1024

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dense 10 - -

1/26/2022, 3:16:42 PM

59%
spectr-dense-e6a
Show logs
PERFORMANCE
LATENCY
6 ms of 150 ms
RAM
26 kB of 256 kB
ROM
21 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 250 ms

SPECTRAL-ANALYSIS

1024

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

Type Filters Kernel Rate
dense 80 - -
dropout - - 0.5
dense 40 - -
dropout - - 0.5

1/26/2022, 3:13:49 PM

59%
spectr-dense-035
Show logs
PERFORMANCE
LATENCY
8 ms of 150 ms
RAM
10 kB of 256 kB
ROM
25 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

SPECTRAL-ANALYSIS

128

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

Type Filters Kernel Rate
dense 80 - -
dense 40 - -

1/26/2022, 3:17:04 PM

59%
spectr-dense-f4a
Show logs
PERFORMANCE
LATENCY
2 ms of 150 ms
RAM
26 kB of 256 kB
ROM
28 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

SPECTRAL-ANALYSIS

1024

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

Type Filters Kernel Rate
dense 80 - -
dropout - - 0.5
dense 40 - -
dropout - - 0.5

1/26/2022, 3:23:46 PM

56%
spectr-dense-6cc
Show logs
PERFORMANCE
LATENCY
8 ms of 150 ms
RAM
26 kB of 256 kB
ROM
26 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

SPECTRAL-ANALYSIS

1024

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

Type Filters Kernel Rate
dense 80 - -
dropout - - 0.25
dense 40 - -
dropout - - 0.25
dense 20 - -
dropout - - 0.25

1/26/2022, 3:14:55 PM

56%
spectr-dense-a5d
Show logs
PERFORMANCE
LATENCY
8 ms of 150 ms
RAM
25 kB of 256 kB
ROM
25 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

SPECTRAL-ANALYSIS

1024

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

Type Filters Kernel Rate
dense 80 - -
dropout - - 0.25
dense 40 - -
dropout - - 0.25
dense 20 - -
dropout - - 0.25

1/26/2022, 3:20:20 PM

53%
spectr-dense-837
Show logs
PERFORMANCE
LATENCY
2 ms of 150 ms
RAM
10 kB of 256 kB
ROM
21 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

SPECTRAL-ANALYSIS

128

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dense 10 - -

1/26/2022, 3:14:08 PM

53%
spectr-dense-d89
Show logs
PERFORMANCE
LATENCY
2 ms of 150 ms
RAM
10 kB of 256 kB
ROM
21 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

SPECTRAL-ANALYSIS

128

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dense 10 - -

1/26/2022, 3:16:25 PM

53%
spectr-dense-034
Show logs
PERFORMANCE
LATENCY
4 ms of 150 ms
RAM
10 kB of 256 kB
ROM
21 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 250 ms

SPECTRAL-ANALYSIS

128

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dense 10 - -

1/26/2022, 3:21:26 PM

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