Edge Impulse Inc. / Tutorial: Recognize sounds from audio - TI LaunchXL 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

Continuous audio

Cortex-M7 216MHz

100 ms

340 kB

1024 kB

Filters

Status

DSP type

Network type

View

Data set

Precision

Sort

General

F1-score

Precision

Recall

100%
spectr-conv1d-99c
Show logs
PERFORMANCE
LATENCY
34 ms of 100 ms
RAM
33 kB of 340 kB
ROM
34 kB of 1024 kB
DSP NN Unused
INPUT

2000 ms | 2000 ms

SPECTROGRAM

0.05 | 0.025 | -52

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/28/2021, 1:46:08 PM

99%
mfe-conv1d-1ca
Show logs
PERFORMANCE
LATENCY
6 ms of 100 ms
RAM
24 kB of 340 kB
ROM
52 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
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.5
dense 64 - -
dropout - - 0.5

7/28/2021, 1:55:57 PM

99%
mfe-conv1d-489
Show logs
PERFORMANCE
LATENCY
12 ms of 100 ms
RAM
25 kB of 340 kB
ROM
62 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

MFE

0.02 | 0.02 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/28/2021, 1:50:53 PM

99%
spectr-conv1d-4f5
Show logs
PERFORMANCE
LATENCY
48 ms of 100 ms
RAM
40 kB of 340 kB
ROM
73 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

SPECTROGRAM

0.025 | 0.0125 | -72

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

7/28/2021, 1:50:23 PM

99%
mfe-conv1d-222
Show logs
PERFORMANCE
LATENCY
18 ms of 100 ms
RAM
24 kB of 340 kB
ROM
71 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
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
dropout - - 0.25

7/28/2021, 1:48:40 PM

99%
mfe-conv1d-523
Show logs
PERFORMANCE
LATENCY
6 ms of 100 ms
RAM
28 kB of 340 kB
ROM
34 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

MFE

0.032 | 0.016 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/28/2021, 1:46:13 PM

94%
spectr-conv1d-81a
Show logs
PERFORMANCE
LATENCY
52 ms of 100 ms
RAM
44 kB of 340 kB
ROM
169 kB of 1024 kB
DSP NN Unused
INPUT

2000 ms | 2000 ms

SPECTROGRAM

0.05 | 0.025 | -32

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

7/28/2021, 1:44:56 PM

91%
mfe-conv1d-01b
Show logs
PERFORMANCE
LATENCY
22 ms of 100 ms
RAM
27 kB of 340 kB
ROM
72 kB of 1024 kB
DSP NN Unused
INPUT

2000 ms | 1000 ms

MFE

0.05 | 0.05 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/28/2021, 1:45:17 PM

87%
spectr-conv2d-2bf
Show logs
PERFORMANCE
LATENCY
70 ms of 100 ms
RAM
25 kB of 340 kB
ROM
101 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

SPECTROGRAM

0.075 | 0.075 | -32

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/28/2021, 1:55:38 PM

86%
mfcc-conv1d-536
Show logs
PERFORMANCE
LATENCY
14 ms of 100 ms
RAM
39 kB of 340 kB
ROM
150 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

MFCC

0.02 | 0.02 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/28/2021, 1:50:36 PM

86%
mfe-conv2d-5aa
Show logs
PERFORMANCE
LATENCY
34 ms of 100 ms
RAM
27 kB of 340 kB
ROM
57 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
conv2d 8 3 -
conv2d 16 3 -
dropout - - 0.25

7/28/2021, 1:49:30 PM

84%
mfe-conv2d-949
Show logs
PERFORMANCE
LATENCY
106 ms of 100 ms
Exceeds target by 6 ms
RAM
37 kB of 340 kB
ROM
59 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
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
dropout - - 0.5

7/28/2021, 1:53:58 PM

84%
mfcc-conv2d-2eb
Show logs
PERFORMANCE
LATENCY
52 ms of 100 ms
RAM
29 kB of 340 kB
ROM
67 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

MFCC

0.05 | 0.025 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/28/2021, 1:54:46 PM

84%
mfcc-conv2d-cd9
Show logs
PERFORMANCE
LATENCY
82 ms of 100 ms
RAM
26 kB of 340 kB
ROM
57 kB of 1024 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

MFCC

0.032 | 0.032 | 32

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/28/2021, 1:49:34 PM

83%
mfcc-conv2d-c61
Show logs
PERFORMANCE
LATENCY
42 ms of 100 ms
RAM
30 kB of 340 kB
ROM
39 kB of 1024 kB
DSP NN Unused
INPUT

2000 ms | 1000 ms

MFCC

0.05 | 0.05 | 32

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

7/28/2021, 1:54:40 PM

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