Edge Impulse Inc. / Tutorial: Continuous motion recognition 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

Cortex-M7 216MHz

50 ms

340 kB

1024 kB

Filters

Status

DSP type

Network type

View

Data set

Precision

Sort

General

F1-score

Precision

Recall

100%
spectr-dense-217
Show logs
PERFORMANCE
LATENCY
2 ms of 50 ms
RAM
25 kB of 340 kB
ROM
26 kB of 1024 kB
DSP NN Unused
INPUT

4000 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

12/21/2021, 2:47:46 PM

100%
spectr-dense-e2b
Show logs
PERFORMANCE
LATENCY
2 ms of 50 ms
RAM
22 kB of 340 kB
ROM
28 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 - -

12/21/2021, 2:50:35 PM

100%
spectr-dense-9ea
Show logs
PERFORMANCE
LATENCY
2 ms of 50 ms
RAM
22 kB of 340 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 20 - -
dense 10 - -
dense 5 - -

12/21/2021, 2:50:57 PM

100%
spectr-dense-e40
Show logs
PERFORMANCE
LATENCY
2 ms of 50 ms
RAM
25 kB of 340 kB
ROM
26 kB of 1024 kB
DSP NN Unused
INPUT

4000 ms | 2000 ms

SPECTRAL-ANALYSIS

1024

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

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

12/21/2021, 2:47:41 PM

100%
spectr-dense-e87
Show logs
PERFORMANCE
LATENCY
2 ms of 50 ms
RAM
8 kB of 340 kB
ROM
19 kB of 1024 kB
DSP NN Unused
INPUT

4000 ms | 4000 ms

SPECTRAL-ANALYSIS

128

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

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

12/21/2021, 2:51:35 PM

100%
spectr-dense-e36
Show logs
PERFORMANCE
LATENCY
2 ms of 50 ms
RAM
24 kB of 340 kB
ROM
22 kB of 1024 kB
DSP NN Unused
INPUT

4000 ms | 1000 ms

SPECTRAL-ANALYSIS

1024

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

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

12/21/2021, 2:47:31 PM

100%
spectr-dense-8c1
Show logs
PERFORMANCE
LATENCY
2 ms of 50 ms
RAM
22 kB of 340 kB
ROM
26 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 - - 0.25
dense 40 - -
dropout - - 0.25
dense 20 - -
dropout - - 0.25

12/21/2021, 2:54:22 PM

100%
spectr-dense-41b
Show logs
PERFORMANCE
LATENCY
2 ms of 50 ms
RAM
8 kB of 340 kB
ROM
45 kB of 1024 kB
DSP NN Unused
INPUT

4000 ms | 4000 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

12/21/2021, 2:53:51 PM

100%
spectr-dense-b16
Show logs
PERFORMANCE
LATENCY
2 ms of 50 ms
RAM
25 kB of 340 kB
ROM
26 kB of 1024 kB
DSP NN Unused
INPUT

4000 ms | 2000 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
dense 20 - -
dropout - - 0.5

12/21/2021, 2:47:44 PM

100%
spectr-dense-156
Show logs
PERFORMANCE
LATENCY
2 ms of 50 ms
RAM
8 kB of 340 kB
ROM
45 kB of 1024 kB
DSP NN Unused
INPUT

4000 ms | 4000 ms

SPECTRAL-ANALYSIS

128

ACCURACY
NEURAL NETWORK (KERAS)

0.0005 | 30

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

12/21/2021, 2:53:53 PM

100%
spectr-dense-c37
Show logs
PERFORMANCE
LATENCY
2 ms of 50 ms
RAM
21 kB of 340 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 - -
dropout - - 0.25
dense 40 - -
dropout - - 0.25

12/21/2021, 2:56:23 PM

100%
spectr-dense-b01
Show logs
PERFORMANCE
LATENCY
2 ms of 50 ms
RAM
21 kB of 340 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 - -
dropout - - 0.5
dense 40 - -
dropout - - 0.5

12/21/2021, 2:57:46 PM

100%
spectr-dense-938
Show logs
PERFORMANCE
LATENCY
2 ms of 50 ms
RAM
24 kB of 340 kB
ROM
25 kB of 1024 kB
DSP NN Unused
INPUT

4000 ms | 4000 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

12/21/2021, 2:56:08 PM

100%
spectr-dense-525
Show logs
PERFORMANCE
LATENCY
2 ms of 50 ms
RAM
21 kB of 340 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 - -
dropout - - 0.5
dense 40 - -
dropout - - 0.5
dense 20 - -
dropout - - 0.5

12/21/2021, 2:59:35 PM

100%
spectr-dense-24f
Show logs
PERFORMANCE
LATENCY
2 ms of 50 ms
RAM
6 kB of 340 kB
ROM
28 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 80 - -
dropout - - 0.5
dense 40 - -
dropout - - 0.5
dense 20 - -
dropout - - 0.5

12/21/2021, 3:00:35 PM

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