george / vibration-analysis-model-v20230319 Public
Target: Nordic nRF9160 DK (Cortex-M33 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

Nordic nRF9160 DK (Cortex-M33 64MHz)

100 ms

256 kB

1024 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

Run #7 (Mar 20 2024, 05:27:33, finished) Run #6 (Mar 19 2024, 16:04:20, running) Run #5 (Mar 19 2024, 15:23:06, finished) Run #4 (Mar 19 2024, 14:50:22, finished) Run #3 (Mar 19 2024, 11:38:33, finished) Run #2 (Mar 19 2024, 09:48:08, finished) Run #1 (Mar 19 2024, 09:18:38, cancelled)
9%
spectr-dense-8cd
PERFORMANCE
LATENCY
4 ms of 100 ms
RAM
3 kB of 256 kB
ROM
21 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTRAL-ANALYSIS

64

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 9%

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

3/19/2024, 4:10:55 PM

2%
spectr-dense-5d5
PERFORMANCE
LATENCY
4 ms of 100 ms
RAM
3 kB of 256 kB
ROM
18 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 2%

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

3/19/2024, 4:12:41 PM

spectr-dense-f6a
PERFORMANCE
LATENCY
4 ms of 100 ms
RAM
3 kB of 256 kB
ROM
18 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
250 ms |
Enabled

SPECTRAL-ANALYSIS

64

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 0%

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

3/19/2024, 4:10:21 PM

21%
spectr-dense-08e
PERFORMANCE
LATENCY
4 ms of 100 ms
RAM
2 kB of 256 kB
ROM
17 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 21%

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

3/19/2024, 4:10:07 PM

20%
spectr-dense-5bd
PERFORMANCE
LATENCY
4 ms of 100 ms
RAM
2 kB of 256 kB
ROM
16 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 20%

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

3/19/2024, 4:07:46 PM

17%
spectr-dense-de7
PERFORMANCE
LATENCY
4 ms of 100 ms
RAM
3 kB of 256 kB
ROM
18 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

SPECTRAL-ANALYSIS

16

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 17%

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

3/19/2024, 4:09:44 PM

spectr-dense-df3
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

SPECTRAL-ANALYSIS

64

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30

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

raw-dense-b1f
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

RAW

1

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30

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

spectr-dense-a32
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

1000 ms |
250 ms |
Enabled

SPECTRAL-ANALYSIS

Parameter Value
wavelet bior1.3
analysis-type Wavelet
wavelet-level 2

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30

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

spectr-dense-489
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

SPECTRAL-ANALYSIS

Parameter Value
wavelet haar
analysis-type Wavelet
wavelet-level 2

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30

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

raw-dense-788
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

RAW

1

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30

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

raw-dense-6c8
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

RAW

1

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30

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

spectr-dense-fbd
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTRAL-ANALYSIS

Parameter Value
wavelet haar
analysis-type Wavelet
wavelet-level 1

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30

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

raw-dense-60a
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

1000 ms |
250 ms |
Enabled

RAW

1

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30

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

spectr-dense-a39
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

1000 ms |
250 ms |
Enabled

SPECTRAL-ANALYSIS

Parameter Value
wavelet bior1.3
analysis-type Wavelet
wavelet-level 2

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30

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

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