Edge Impulse Inc. / Tutorial: Recognize sounds from audio Public
Clone this project

EON Tuner

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

Keyword spotting

Nordic nRF9160 DK (Cortex-M33 64MHz)

100 ms

256 kB

1024 kB

Filters

Status

DSP type

Network type

View

Data set

Precision

Sort

General

F1-score

Precision

Recall

100%
mfe-conv1d-656
Show logs
PERFORMANCE
LATENCY
30 ms of 100 ms
RAM
20 kB of 256 kB
ROM
56 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

MFE

0.032 | 0.032 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

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

100%
spectr-conv1d-97d
Show logs
PERFORMANCE
LATENCY
119 ms of 100 ms
Exceeds target by 19 ms
RAM
21 kB of 256 kB
ROM
47 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

SPECTROGRAM

0.075 | 0.0375 | -52

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

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

100%
spectr-conv1d-ee2
Show logs
PERFORMANCE
LATENCY
41 ms of 100 ms
RAM
23 kB of 256 kB
ROM
46 kB of 1024 kB
DSP NN Unused
INPUT

2000 ms | 1000 ms

SPECTROGRAM

0.075 | 0.075 | -72

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

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

100%
mfe-conv1d-a7e
Show logs
PERFORMANCE
LATENCY
28 ms of 100 ms
RAM
24 kB of 256 kB
ROM
43 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

MFE

0.05 | 0.025 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

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

100%
mfe-conv1d-6de
Show logs
PERFORMANCE
LATENCY
16 ms of 100 ms
RAM
21 kB of 256 kB
ROM
37 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

MFE

0.05 | 0.05 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

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

100%
spectr-conv1d-fea
Show logs
PERFORMANCE
LATENCY
59 ms of 100 ms
RAM
27 kB of 256 kB
ROM
46 kB of 1024 kB
DSP NN Unused
INPUT

2000 ms | 2000 ms

SPECTROGRAM

0.05 | 0.05 | -72

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

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

100%
mfe-conv1d-293
Show logs
PERFORMANCE
LATENCY
116 ms of 100 ms
Exceeds target by 16 ms
RAM
26 kB of 256 kB
ROM
72 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

MFE

0.032 | 0.032 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

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

100%
spectr-conv1d-b13
Show logs
PERFORMANCE
LATENCY
109 ms of 100 ms
Exceeds target by 9 ms
RAM
31 kB of 256 kB
ROM
77 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

SPECTROGRAM

0.025 | 0.025 | -52

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

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

100%
mfe-conv1d-3cd
Show logs
PERFORMANCE
LATENCY
49 ms of 100 ms
RAM
24 kB of 256 kB
ROM
46 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

MFE

0.05 | 0.05 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

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

100%
spectr-conv1d-e0b
Show logs
PERFORMANCE
LATENCY
72 ms of 100 ms
RAM
22 kB of 256 kB
ROM
46 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

SPECTROGRAM

0.075 | 0.0375 | -52

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

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

100%
mfe-conv2d-529
Show logs
PERFORMANCE
LATENCY
170 ms of 100 ms
Exceeds target by 70 ms
RAM
21 kB of 256 kB
ROM
66 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

MFE

0.05 | 0.05 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

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

100%
spectr-conv1d-c6b
Show logs
PERFORMANCE
LATENCY
21 ms of 100 ms
RAM
17 kB of 256 kB
ROM
41 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

SPECTROGRAM

0.05 | 0.05 | -72

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

12/17/2021, 10:31:23 PM

100%
mfe-conv1d-cd2
Show logs
PERFORMANCE
LATENCY
31 ms of 100 ms
RAM
26 kB of 256 kB
ROM
46 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

MFE

0.05 | 0.025 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

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

100%
spectr-conv1d-bbc
Show logs
PERFORMANCE
LATENCY
33 ms of 100 ms
RAM
22 kB of 256 kB
ROM
46 kB of 1024 kB
DSP NN Unused
INPUT

2000 ms | 2000 ms

SPECTROGRAM

0.075 | 0.075 | -72

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

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

100%
spectr-conv1d-774
Show logs
PERFORMANCE
LATENCY
100 ms of 100 ms
RAM
21 kB of 256 kB
ROM
90 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

SPECTROGRAM

0.05 | 0.05 | -52

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

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

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