Edge Impulse Inc. / Tutorial: Recognize sounds from audio Public
The EON Tuner helps you find the most optimal architecture for your embedded machine-learning application. Clone this project to use the EON Tuner.

Target

No name set

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

100%
spectr-conv1d-cb4
PERFORMANCE
LATENCY
11 ms of 100 ms
RAM
17 kB of 8388608 kB
ROM
41 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.05 | 0.05 | -72

ACCURACY (KERAS)

12/17/2021, 10:21:40 PM

100%
mfe-conv1d-270
PERFORMANCE
LATENCY
15 ms of 100 ms
RAM
20 kB of 8388608 kB
ROM
56 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFE

0.032 | 0.032 | 40

ACCURACY (KERAS)

12/17/2021, 10:24:17 PM

100%
spectr-conv1d-ecb
PERFORMANCE
LATENCY
57 ms of 100 ms
RAM
21 kB of 8388608 kB
ROM
47 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.075 | 0.0375 | -52

ACCURACY (KERAS)

12/17/2021, 10:24:58 PM

100%
spectr-conv1d-387
PERFORMANCE
LATENCY
20 ms of 100 ms
RAM
23 kB of 8388608 kB
ROM
46 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

2000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.075 | 0.075 | -72

ACCURACY (KERAS)

12/17/2021, 10:22:11 PM

100%
mfe-conv1d-43b
PERFORMANCE
LATENCY
11 ms of 100 ms
RAM
21 kB of 8388608 kB
ROM
43 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.032 | 40

ACCURACY (KERAS)

12/17/2021, 10:26:02 PM

100%
mfe-conv1d-de7
PERFORMANCE
LATENCY
14 ms of 100 ms
RAM
24 kB of 8388608 kB
ROM
43 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)

12/17/2021, 10:25:59 PM

100%
spectr-conv1d-517
PERFORMANCE
LATENCY
20 ms of 100 ms
RAM
23 kB of 8388608 kB
ROM
46 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.025 | 0.025 | -72

ACCURACY (KERAS)

12/17/2021, 10:27:20 PM

100%
spectr-conv1d-03a
PERFORMANCE
LATENCY
28 ms of 100 ms
RAM
26 kB of 8388608 kB
ROM
46 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.025 | 0.025 | -52

ACCURACY (KERAS)

12/17/2021, 10:27:57 PM

100%
mfe-conv1d-69a
PERFORMANCE
LATENCY
8 ms of 100 ms
RAM
21 kB of 8388608 kB
ROM
37 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)

12/17/2021, 10:27:45 PM

100%
spectr-conv1d-edb
PERFORMANCE
LATENCY
28 ms of 100 ms
RAM
27 kB of 8388608 kB
ROM
46 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

2000 ms |
2000 ms |
Enabled

SPECTROGRAM

0.05 | 0.05 | -72

ACCURACY (KERAS)

12/17/2021, 10:27:54 PM

100%
mfe-conv1d-cc5
PERFORMANCE
LATENCY
55 ms of 100 ms
RAM
26 kB of 8388608 kB
ROM
72 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.032 | 40

ACCURACY (KERAS)

12/17/2021, 10:29:04 PM

100%
spectr-conv1d-72e
PERFORMANCE
LATENCY
52 ms of 100 ms
RAM
31 kB of 8388608 kB
ROM
77 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.025 | 0.025 | -52

ACCURACY (KERAS)

12/17/2021, 10:29:19 PM

100%
mfe-conv1d-697
PERFORMANCE
LATENCY
24 ms of 100 ms
RAM
24 kB of 8388608 kB
ROM
46 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)

12/17/2021, 10:29:37 PM

100%
spectr-conv1d-bff
PERFORMANCE
LATENCY
34 ms of 100 ms
RAM
22 kB of 8388608 kB
ROM
46 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.075 | 0.0375 | -52

ACCURACY (KERAS)

12/17/2021, 10:29:43 PM

100%
mfe-conv2d-421
PERFORMANCE
LATENCY
81 ms of 100 ms
RAM
21 kB of 8388608 kB
ROM
66 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)

12/17/2021, 10:31:08 PM