Deb / wio-shake-lift Public

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

Continuous motion

Seeed Studio Wio Terminal (Cortex-M4F 120MHz)

100 ms

192 kB

4096 kB

Filters

Status

DSP type

Network type

View

Data set

Precision

Sort

General

F1-score

Precision

Recall

93%
spectr-dense-923
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
6 kB of 192 kB
ROM
23 kB of 4096 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 - -

9/30/2021, 7:24:23 PM

93%
spectr-dense-8e1
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
6 kB of 192 kB
ROM
18 kB of 4096 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

SPECTRAL-ANALYSIS

128

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

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

9/30/2021, 7:27:14 PM

93%
spectr-dense-181
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
6 kB of 192 kB
ROM
25 kB of 4096 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

SPECTRAL-ANALYSIS

128

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

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

9/30/2021, 7:28:37 PM

93%
spectr-dense-58e
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
6 kB of 192 kB
ROM
18 kB of 4096 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 - -
dense 20 - -

9/30/2021, 7:32:12 PM

92%
spectr-dense-bb0
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
6 kB of 192 kB
ROM
20 kB of 4096 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 - -

9/30/2021, 7:24:05 PM

92%
spectr-dense-9a7
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
6 kB of 192 kB
ROM
20 kB of 4096 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 - -

9/30/2021, 7:24:07 PM

92%
spectr-dense-2ab
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
6 kB of 192 kB
ROM
19 kB of 4096 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 - -

9/30/2021, 7:28:52 PM

92%
spectr-dense-2e3
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
6 kB of 192 kB
ROM
23 kB of 4096 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 - -
dropout - - 0.25
dense 40 - -
dropout - - 0.25

9/30/2021, 7:29:14 PM

89%
spectr-dense-4fb
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
6 kB of 192 kB
ROM
25 kB of 4096 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

SPECTRAL-ANALYSIS

128

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

Type Filters Kernel Rate
dense 80 - -
dropout - - 0.5
dense 40 - -
dropout - - 0.5
dense 20 - -
dropout - - 0.5

9/30/2021, 7:25:00 PM

89%
spectr-dense-d00
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
6 kB of 192 kB
ROM
24 kB of 4096 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 - -
dropout - - 0.5
dense 40 - -
dropout - - 0.5
dense 20 - -
dropout - - 0.5

9/30/2021, 7:28:43 PM

89%
spectr-dense-c8d
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
6 kB of 192 kB
ROM
20 kB of 4096 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 - -
dropout - - 0.25
dense 20 - -
dropout - - 0.25
dense 10 - -
dropout - - 0.25

9/30/2021, 7:29:39 PM

89%
spectr-dense-1e4
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
6 kB of 192 kB
ROM
23 kB of 4096 kB
DSP NN Unused
INPUT

1000 ms | 250 ms

SPECTRAL-ANALYSIS

128

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

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

9/30/2021, 7:29:52 PM

88%
spectr-dense-488
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
22 kB of 192 kB
ROM
18 kB of 4096 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

9/30/2021, 7:22:38 PM

88%
spectr-dense-0be
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
22 kB of 192 kB
ROM
20 kB of 4096 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 - -

9/30/2021, 7:23:31 PM

88%
spectr-dense-5a2
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
6 kB of 192 kB
ROM
20 kB of 4096 kB
DSP NN Unused
INPUT

1000 ms | 250 ms

SPECTRAL-ANALYSIS

128

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

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

9/30/2021, 7:22:53 PM