Marcelo Rovai / IESTI01 - Motion Classification - Version 2 Public
Target: Arduino Nano 33 BLE Sense (Cortex-M4F 64MHz) 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

Arduino Nano 33 BLE Sense (Cortex-M4F 64MHz)

100 ms

256 kB

1024 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

50%
spectr-dense-4ac
PERFORMANCE
LATENCY
29 ms of 100 ms
RAM
15 kB of 256 kB
ROM
19 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 50%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dense 10 - -
dropout - - 0.25

3/16/2023, 7:19:56 PM

spectr-dense-434
PERFORMANCE
LATENCY
111 ms of 100 ms
Exceeds target by 11 ms
RAM
10 kB of 256 kB
ROM
17 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 0%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dense 10 - -
dropout - - 0.5

3/16/2023, 7:20:05 PM

75%
spectr-dense-eb2
PERFORMANCE
LATENCY
34 ms of 100 ms
RAM
15 kB of 256 kB
ROM
20 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 75%

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

3/16/2023, 7:31:06 PM

63%
spectr-dense-7ec
PERFORMANCE
LATENCY
34 ms of 100 ms
RAM
15 kB of 256 kB
ROM
20 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 63%

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

3/16/2023, 7:36:37 PM

50%
spectr-dense-e53
PERFORMANCE
LATENCY
111 ms of 100 ms
Exceeds target by 11 ms
RAM
10 kB of 256 kB
ROM
16 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 50%

Type Filters Kernel Rate
dense 20 - -
dense 10 - -
dense 5 - -
dropout - - 0.5

3/16/2023, 7:20:14 PM

50%
spectr-dense-f52
PERFORMANCE
LATENCY
32 ms of 100 ms
RAM
15 kB of 256 kB
ROM
19 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 50%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dense 10 - -
dropout - - 0.25

3/16/2023, 7:27:11 PM

50%
spectr-dense-8fc
PERFORMANCE
LATENCY
29 ms of 100 ms
RAM
15 kB of 256 kB
ROM
19 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 50%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dense 10 - -
dropout - - 0.5

3/16/2023, 7:32:35 PM

50%
spectr-dense-e8a
PERFORMANCE
LATENCY
111 ms of 100 ms
Exceeds target by 11 ms
RAM
10 kB of 256 kB
ROM
16 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 50%

Type Filters Kernel Rate
dense 20 - -
dense 10 - -
dense 5 - -
dropout - - 0.25

3/16/2023, 7:34:03 PM

38%
spectr-dense-5b7
PERFORMANCE
LATENCY
29 ms of 100 ms
RAM
14 kB of 256 kB
ROM
16 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 38%

Type Filters Kernel Rate
dense 20 - -
dense 10 - -
dropout - - 0.25

3/16/2023, 7:23:04 PM

38%
spectr-dense-770
PERFORMANCE
LATENCY
29 ms of 100 ms
RAM
14 kB of 256 kB
ROM
16 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 38%

Type Filters Kernel Rate
dense 20 - -
dense 10 - -
dropout - - 0.5

3/16/2023, 7:23:09 PM

38%
spectr-dense-560
PERFORMANCE
LATENCY
34 ms of 100 ms
RAM
10 kB of 256 kB
ROM
20 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTRAL-ANALYSIS

64

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 38%

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

3/16/2023, 7:23:43 PM

38%
spectr-dense-606
PERFORMANCE
LATENCY
32 ms of 100 ms
RAM
15 kB of 256 kB
ROM
16 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 38%

Type Filters Kernel Rate
dense 20 - -
dense 10 - -
dropout - - 0.25

3/16/2023, 7:27:44 PM

38%
spectr-dense-a96
PERFORMANCE
LATENCY
34 ms of 100 ms
RAM
10 kB of 256 kB
ROM
20 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTRAL-ANALYSIS

64

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 38%

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

3/16/2023, 7:28:39 PM

25%
spectr-dense-c43
PERFORMANCE
LATENCY
29 ms of 100 ms
RAM
15 kB of 256 kB
ROM
19 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 25%

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

3/16/2023, 7:25:51 PM

25%
spectr-dense-0a7
PERFORMANCE
LATENCY
29 ms of 100 ms
RAM
15 kB of 256 kB
ROM
19 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

10000 ms |
10000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 25%

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

3/16/2023, 7:26:25 PM

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