Tobias Lindhorst / Alerto2 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

Run #2

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

Run #5 (Mar 25 2025, 13:02:33, finished) Run #4 (Mar 25 2025, 12:40:42, failed) Run #3 (Mar 25 2025, 12:06:07, failed) Run #2 (Mar 25 2025, 11:59:56, failed) Run #1 (Mar 25 2025, 11:49:34, failed)
86%
mfe-conv1d-9fe
PERFORMANCE
LATENCY
12 ms of 100 ms
RAM
9 kB of 256 kB
ROM
70 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

2000 ms |
2000 ms |
Enabled

MFE

0.05 | 0.05 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 86%

Type Filters Kernel Rate
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
dropout - - 0.25

3/25/2025, 12:03:36 PM

82%
mfe-conv1d-a71
PERFORMANCE
LATENCY
5 ms of 100 ms
RAM
6 kB of 256 kB
ROM
35 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

2000 ms |
2000 ms |
Enabled

MFE

0.05 | 0.05 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 82%

Type Filters Kernel Rate
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
dropout - - 0.5

3/25/2025, 12:04:02 PM

62%
mfe-conv1d-cb7
PERFORMANCE
LATENCY
124 ms of 100 ms
Exceeds target by 24 ms
RAM
16 kB of 256 kB
ROM
32 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

2000 ms |
500 ms |
Enabled

MFE

0.05 | 0.05 | 32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 62%

Type Filters Kernel Rate
conv1d 8 3 -
conv1d 16 3 -
dropout - - 0.25

3/25/2025, 12:04:57 PM

0%
spectr-conv1d-dea
PERFORMANCE
LATENCY
13 ms of 100 ms
RAM
13 kB of 256 kB
ROM
34 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

2000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.025 | 0.025 | -32

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 0%

Type Filters Kernel Rate
conv1d 8 3 -
conv1d 16 3 -
dropout - - 0.25

3/25/2025, 12:05:26 PM

0%
spectr-conv1d-74a
PERFORMANCE
LATENCY
7 ms of 100 ms
RAM
9 kB of 256 kB
ROM
36 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

2000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.05 | 0.05 | -52

ACCURACY (OVERALL)
CLASSIFICATION

0.005 | 100 | 0%

Type Filters Kernel Rate
Data augmentation
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
dropout - - 0.25

3/25/2025, 12:04:24 PM

mfe-conv1d-58e
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

2000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.05 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100

Type Filters Kernel Rate
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
dropout - - 0.5

spectr-conv1d-010
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

2000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.075 | 0.075 | -52

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100

Type Filters Kernel Rate
conv1d 8 3 -
conv1d 16 3 -
dropout - - 0.25

spectr-conv1d-1d8
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

2000 ms |
2000 ms |
Enabled

SPECTROGRAM

0.075 | 0.075 | -32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100

Type Filters Kernel Rate
Data augmentation
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.25

mfe-conv1d-725
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

2000 ms |
500 ms |
Enabled

MFE

0.05 | 0.05 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100

Type Filters Kernel Rate
Data augmentation
conv1d 16 3 -
conv1d 32 3 -
dropout - - 0.25

spectr-conv1d-d37
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

2000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.05 | 0.05 | -32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100

Type Filters Kernel Rate
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.5

mfcc-conv1d-31f
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

2000 ms |
500 ms |
Enabled

MFCC

0.05 | 0.05 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100

Type Filters Kernel Rate
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
dropout - - 0.25

mfcc-conv1d-bbe
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

2000 ms |
2000 ms |
Enabled

MFCC

0.05 | 0.05 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100

Type Filters Kernel Rate
conv1d 8 3 -
conv1d 16 3 -
dropout - - 0.25

mfe-conv1d-615
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

2000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100

Type Filters Kernel Rate
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
dropout - - 0.5

spectr-conv1d-871
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

2000 ms |
500 ms |
Enabled

SPECTROGRAM

0.025 | 0.025 | -32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100

Type Filters Kernel Rate
Data augmentation
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.25

mfcc-conv1d-82a
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

2000 ms |
1000 ms |
Enabled

MFCC

0.05 | 0.05 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100

Type Filters Kernel Rate
conv1d 8 3 -
conv1d 16 3 -
dropout - - 0.5

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