M0JPI / Sound Test Public
Target: Raspberry Pi 4 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

RPi4-5th-tune

Raspberry Pi 4

100 ms

8388608 kB

33554432 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

Run #12 - RPi4-6th-tune (Sep 26 2024, 14:26:50, finished) Run #11 - RPi4-5th-tune (Sep 08 2024, 17:00:46, finished) Run #10 - RPi4-5th-tune (Sep 01 2024, 14:33:07, finished) Run #9 - RPi4-5th-tune (Aug 31 2024, 20:58:58, finished) Run #8 - RPi4-5th-tune (Aug 27 2024, 19:45:25, finished) Run #7 - RPi4-5th-tune (Aug 26 2024, 15:20:52, running) Run #6 - RPi4-5th-tune (Aug 01 2024, 19:49:02, finished) Run #5 - RPi4-5th-tune (Aug 01 2024, 19:35:52, finished) Run #4 - RPi4-4rd-tune (Aug 01 2024, 18:58:40, finished) Run #3 - RPi4-3rd-tune (Aug 01 2024, 17:51:22, finished) Run #2 - RPi4-1st-tune (Aug 01 2024, 15:33:53, finished) Run #1 - RPi4-1st-tune (Jul 28 2024, 15:38:22, finished)
100%
mfe-conv1d-9a8
PERFORMANCE
LATENCY
12 ms of 100 ms
RAM
61 kB of 8388608 kB
ROM
181 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

5000 ms |
5000 ms |
Enabled

MFE

0.02 | 0.02 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 100%

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

8/27/2024, 7:56:15 PM

100%
mfcc-conv2d-c40
PERFORMANCE
LATENCY
12 ms of 100 ms
RAM
43 kB of 8388608 kB
ROM
58 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

5000 ms |
5000 ms |
Enabled

MFCC

0.05 | 0.05 | 40

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 100%

Type Filters Kernel Rate
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
dropout - - 0.25

8/27/2024, 7:52:32 PM

100%
mfcc-conv2d-376
PERFORMANCE
LATENCY
15 ms of 100 ms
RAM
50 kB of 8388608 kB
ROM
58 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

6000 ms |
6000 ms |
Enabled

MFCC

0.05 | 0.05 | 40

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 100%

Type Filters Kernel Rate
Data augmentation
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
dropout - - 0.25

8/27/2024, 7:51:26 PM

100%
mfcc-conv2d-82a
PERFORMANCE
LATENCY
15 ms of 100 ms
RAM
50 kB of 8388608 kB
ROM
58 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

6000 ms |
6000 ms |
Enabled

MFCC

0.05 | 0.05 | 40

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 100%

Type Filters Kernel Rate
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
dropout - - 0.25

8/27/2024, 7:48:44 PM

96%
mfe-conv2d-c82
PERFORMANCE
LATENCY
8 ms of 100 ms
RAM
76 kB of 8388608 kB
ROM
44 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

5000 ms |
5000 ms |
Enabled

MFE

0.032 | 0.032 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 96%

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

8/27/2024, 7:57:27 PM

96%
mfe-conv1d-d60
PERFORMANCE
LATENCY
9 ms of 100 ms
RAM
51 kB of 8388608 kB
ROM
179 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

5000 ms |
5000 ms |
Enabled

MFE

0.05 | 0.025 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 96%

Type Filters Kernel Rate
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
conv1d 256 3 -
dropout - - 0.5

8/27/2024, 7:55:28 PM

96%
mfcc-conv2d-ae3
PERFORMANCE
LATENCY
19 ms of 100 ms
RAM
60 kB of 8388608 kB
ROM
40 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

5000 ms |
5000 ms |
Enabled

MFCC

0.032 | 0.032 | 40

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 96%

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

8/27/2024, 7:52:27 PM

96%
mfcc-conv2d-d7f
PERFORMANCE
LATENCY
23 ms of 100 ms
RAM
75 kB of 8388608 kB
ROM
41 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

5000 ms |
5000 ms |
Enabled

MFCC

0.05 | 0.025 | 40

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 96%

Type Filters Kernel Rate
Data augmentation
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
dropout - - 0.25

8/27/2024, 7:50:07 PM

93%
mfcc-conv2d-c9d
PERFORMANCE
LATENCY
28 ms of 100 ms
RAM
94 kB of 8388608 kB
ROM
59 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

5000 ms |
5000 ms |
Enabled

MFCC

0.02 | 0.02 | 40

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 93%

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

8/27/2024, 7:57:37 PM

93%
mfcc-conv2d-c1d
PERFORMANCE
LATENCY
18 ms of 100 ms
RAM
69 kB of 8388608 kB
ROM
41 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

5000 ms |
5000 ms |
Enabled

MFCC

0.05 | 0.025 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 93%

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

8/27/2024, 7:51:20 PM

93%
mfe-conv1d-70e
PERFORMANCE
LATENCY
15 ms of 100 ms
RAM
59 kB of 8388608 kB
ROM
181 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

6000 ms |
6000 ms |
Enabled

MFE

0.05 | 0.025 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 93%

Type Filters Kernel Rate
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
conv1d 256 3 -
dropout - - 0.5

8/27/2024, 7:51:00 PM

89%
mfe-conv1d-71e
PERFORMANCE
LATENCY
12 ms of 100 ms
RAM
49 kB of 8388608 kB
ROM
178 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

6000 ms |
6000 ms |
Enabled

MFE

0.032 | 0.032 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 89%

Type Filters Kernel Rate
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
conv1d 256 3 -
dropout - - 0.5

8/27/2024, 7:50:54 PM

89%
mfcc-conv2d-f48
PERFORMANCE
LATENCY
13 ms of 100 ms
RAM
53 kB of 8388608 kB
ROM
45 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

5000 ms |
5000 ms |
Enabled

MFCC

0.05 | 0.05 | 40

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 89%

Type Filters Kernel Rate
Data augmentation
conv2d 16 3 -
conv2d 32 3 -
dropout - - 0.25

8/27/2024, 7:49:53 PM

85%
mfcc-conv1d-86f
PERFORMANCE
LATENCY
42 ms of 100 ms
RAM
136 kB of 8388608 kB
ROM
192 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

5000 ms |
5000 ms |
Enabled

MFCC

0.02 | 0.01 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 85%

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

8/27/2024, 8:03:00 PM

85%
mfe-conv1d-687
PERFORMANCE
LATENCY
12 ms of 100 ms
RAM
51 kB of 8388608 kB
ROM
179 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

5000 ms |
5000 ms |
Enabled

MFE

0.05 | 0.025 | 32

ACCURACY (KERAS)
CLASSIFICATION

0.005 | 100 | 85%

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

8/27/2024, 7:52:56 PM

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