jonathando8 / EEP564 Project-Audio Classification - Home Security 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

100%
spectr-conv1d-e17
PERFORMANCE
LATENCY
278 ms of 100 ms
Exceeds target by 178 ms
RAM
60 kB of 256 kB
ROM
44 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTROGRAM

0.075 | 0.0375 | -52

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 100%

Type Filters Kernel Rate
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.5

7/23/2024, 2:16:23 PM

99%
spectr-conv1d-588
PERFORMANCE
LATENCY
493 ms of 100 ms
Exceeds target by 393 ms
RAM
71 kB of 256 kB
ROM
49 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTROGRAM

0.025 | 0.025 | -32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 99%

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

7/23/2024, 2:04:13 PM

99%
spectr-conv2d-9b4
PERFORMANCE
LATENCY
875 ms of 100 ms
Exceeds target by 775 ms
RAM
112 kB of 256 kB
ROM
45 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTROGRAM

0.075 | 0.0375 | -52

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 99%

Type Filters Kernel Rate
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
dropout - - 0.5

7/23/2024, 2:17:18 PM

97%
spectr-conv1d-d00
PERFORMANCE
LATENCY
358 ms of 100 ms
Exceeds target by 258 ms
RAM
62 kB of 256 kB
ROM
72 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

3000 ms |
3000 ms |
Enabled

SPECTROGRAM

0.05 | 0.025 | -52

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 97%

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

7/23/2024, 2:11:06 PM

97%
spectr-conv1d-803
PERFORMANCE
LATENCY
133 ms of 100 ms
Exceeds target by 33 ms
RAM
36 kB of 256 kB
ROM
71 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

3000 ms |
3000 ms |
Enabled

SPECTROGRAM

0.075 | 0.075 | -32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 97%

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

7/23/2024, 2:14:31 PM

96%
spectr-conv1d-94b
PERFORMANCE
LATENCY
218 ms of 100 ms
Exceeds target by 118 ms
RAM
51 kB of 256 kB
ROM
72 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

3000 ms |
3000 ms |
Enabled

SPECTROGRAM

0.075 | 0.0375 | -52

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 96%

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

7/23/2024, 2:29:14 PM

96%
spectr-conv2d-9e3
PERFORMANCE
LATENCY
1613 ms of 100 ms
Exceeds target by 1513 ms
RAM
157 kB of 256 kB
ROM
62 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTROGRAM

0.05 | 0.025 | -52

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 96%

Type Filters Kernel Rate
Data augmentation
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
dropout - - 0.5

7/23/2024, 2:10:29 PM

96%
spectr-conv1d-1b1
PERFORMANCE
LATENCY
431 ms of 100 ms
Exceeds target by 331 ms
RAM
74 kB of 256 kB
ROM
73 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTROGRAM

0.025 | 0.025 | -52

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 96%

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

7/23/2024, 2:17:21 PM

96%
spectr-conv1d-cb5
PERFORMANCE
LATENCY
436 ms of 100 ms
Exceeds target by 336 ms
RAM
51 kB of 256 kB
ROM
175 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTROGRAM

0.05 | 0.05 | -32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 96%

Type Filters Kernel Rate
Data augmentation
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
conv1d 256 3 -
dropout - - 0.25

7/23/2024, 2:22:06 PM

96%
spectr-conv1d-01c
PERFORMANCE
LATENCY
674 ms of 100 ms
Exceeds target by 574 ms
RAM
132 kB of 256 kB
ROM
40 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

SPECTROGRAM

0.025 | 0.0125 | -72

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 96%

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

7/23/2024, 2:24:33 PM

92%
spectr-conv2d-1ab
PERFORMANCE
LATENCY
1362 ms of 100 ms
Exceeds target by 1262 ms
RAM
222 kB of 256 kB
ROM
54 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

3000 ms |
3000 ms |
Enabled

SPECTROGRAM

0.025 | 0.0125 | -72

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 92%

Type Filters Kernel Rate
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
dropout - - 0.5

7/23/2024, 2:04:38 PM

89%
spectr-conv1d-62d
PERFORMANCE
LATENCY
254 ms of 100 ms
Exceeds target by 154 ms
RAM
55 kB of 256 kB
ROM
37 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

3000 ms |
3000 ms |
Enabled

SPECTROGRAM

0.025 | 0.025 | -52

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 89%

Type Filters Kernel Rate
Data augmentation
conv1d 16 3 -
conv1d 32 3 -
dropout - - 0.5

7/23/2024, 2:28:19 PM

mfe-conv1d-020
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

MFE

0.05 | 0.025 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100

Type Filters Kernel Rate
Data augmentation
conv1d 16 3 -
conv1d 32 3 -
dropout - - 0.5

mfe-conv1d-ac5
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

3000 ms |
3000 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 -
conv1d 64 3 -
conv1d 128 3 -
dropout - - 0.25

mfcc-conv1d-88c
PERFORMANCE
LATENCY
100 ms
RAM
256 kB
ROM
1024 kB
Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

MFCC

0.05 | 0.05 | 40

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100

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

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