Datasets by Edge Impulse / Audio Classification - Faucet vs noise 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-703
PERFORMANCE
LATENCY
79 ms of 100 ms
RAM
17 kB of 8388608 kB
ROM
45 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, 10:39:28 PM

100%
mfe-conv1d-0b2
PERFORMANCE
LATENCY
52 ms of 100 ms
RAM
26 kB of 8388608 kB
ROM
67 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, 10:39:33 PM

100%
spectr-conv1d-ad7
PERFORMANCE
LATENCY
48 ms of 100 ms
RAM
21 kB of 8388608 kB
ROM
67 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.05 | 0.05 | -52

ACCURACY (KERAS)

12/17/2021, 10:39:36 PM

100%
spectr-conv1d-a8b
PERFORMANCE
LATENCY
56 ms of 100 ms
RAM
26 kB of 8388608 kB
ROM
67 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

SPECTROGRAM

0.05 | 0.025 | -72

ACCURACY (KERAS)

12/17/2021, 10:39:40 PM

100%
mfe-conv1d-17d
PERFORMANCE
LATENCY
19 ms of 100 ms
RAM
24 kB of 8388608 kB
ROM
45 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, 10:37:55 PM

100%
spectr-conv1d-43c
PERFORMANCE
LATENCY
37 ms of 100 ms
RAM
29 kB of 8388608 kB
ROM
70 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

SPECTROGRAM

0.025 | 0.025 | -52

ACCURACY (KERAS)

12/17/2021, 10:37:35 PM

100%
spectr-conv1d-dbd
PERFORMANCE
LATENCY
28 ms of 100 ms
RAM
24 kB of 8388608 kB
ROM
45 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

SPECTROGRAM

0.05 | 0.025 | -72

ACCURACY (KERAS)

12/17/2021, 10:37:50 PM

100%
spectr-conv1d-3b3
PERFORMANCE
LATENCY
27 ms of 100 ms
RAM
37 kB of 8388608 kB
ROM
237 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

2000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.075 | 0.0375 | -72

ACCURACY (KERAS)

12/17/2021, 10:34:34 PM

100%
spectr-conv1d-625
PERFORMANCE
LATENCY
48 ms of 100 ms
RAM
21 kB of 8388608 kB
ROM
90 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

SPECTROGRAM

0.05 | 0.05 | -52

ACCURACY (KERAS)

12/17/2021, 10:34:59 PM

100%
spectr-conv1d-527
PERFORMANCE
LATENCY
16 ms of 100 ms
RAM
22 kB of 8388608 kB
ROM
46 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

2000 ms |
2000 ms |
Enabled

SPECTROGRAM

0.075 | 0.075 | -72

ACCURACY (KERAS)

12/17/2021, 10:32:31 PM

100%
mfe-conv2d-c5c
PERFORMANCE
LATENCY
69 ms of 100 ms
RAM
25 kB of 8388608 kB
ROM
35 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)

12/17/2021, 10:34:48 PM

100%
mfe-conv2d-f23
PERFORMANCE
LATENCY
81 ms of 100 ms
RAM
26 kB of 8388608 kB
ROM
90 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)

12/17/2021, 10:34:56 PM

100%
mfe-conv1d-4d4
PERFORMANCE
LATENCY
15 ms of 100 ms
RAM
26 kB of 8388608 kB
ROM
46 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)

12/17/2021, 10:32:28 PM

100%
spectr-conv1d-9b3
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, 10:31:23 PM

100%
spectr-conv1d-07d
PERFORMANCE
LATENCY
11 ms of 100 ms
RAM
26 kB of 8388608 kB
ROM
61 kB of 33554432 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.075 | 0.0375 | -72

ACCURACY (KERAS)

12/17/2021, 10:30:59 PM