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

Cortex-M4F 80MHz

100 ms

128 kB

1024 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

100%
mfe-conv1d-1ca
PERFORMANCE
LATENCY
17 ms of 100 ms
RAM
24 kB of 128 kB
ROM
52 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.032 | 40

ACCURACY (KERAS)

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

100%
mfe-conv2d-949
PERFORMANCE
LATENCY
311 ms of 100 ms
Exceeds target by 211 ms
RAM
37 kB of 128 kB
ROM
59 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)

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

100%
mfe-conv1d-489
PERFORMANCE
LATENCY
35 ms of 100 ms
RAM
25 kB of 128 kB
ROM
62 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.02 | 0.02 | 40

ACCURACY (KERAS)

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

100%
spectr-conv1d-4f5
PERFORMANCE
LATENCY
141 ms of 100 ms
Exceeds target by 41 ms
RAM
40 kB of 128 kB
ROM
73 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.025 | 0.0125 | -72

ACCURACY (KERAS)

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

100%
mfe-conv1d-222
PERFORMANCE
LATENCY
50 ms of 100 ms
RAM
24 kB of 128 kB
ROM
71 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.032 | 40

ACCURACY (KERAS)

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

100%
mfe-conv2d-5aa
PERFORMANCE
LATENCY
97 ms of 100 ms
RAM
27 kB of 128 kB
ROM
57 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFE

0.032 | 0.032 | 40

ACCURACY (KERAS)

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

100%
mfe-conv1d-523
PERFORMANCE
LATENCY
16 ms of 100 ms
RAM
28 kB of 128 kB
ROM
34 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.016 | 40

ACCURACY (KERAS)

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

100%
spectr-conv1d-99c
PERFORMANCE
LATENCY
99 ms of 100 ms
RAM
33 kB of 128 kB
ROM
34 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

2000 ms |
2000 ms |
Enabled

SPECTROGRAM

0.05 | 0.025 | -52

ACCURACY (KERAS)

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

100%
mfe-conv1d-d51
PERFORMANCE
LATENCY
22 ms of 100 ms
RAM
34 kB of 128 kB
ROM
169 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.032 | 40

ACCURACY (KERAS)

7/28/2021, 1:44:59 PM

99%
mfe-conv2d-737
PERFORMANCE
LATENCY
113 ms of 100 ms
Exceeds target by 13 ms
RAM
30 kB of 128 kB
ROM
113 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.032 | 0.032 | 40

ACCURACY (KERAS)

7/28/2021, 1:51:44 PM

99%
mfe-conv1d-01b
PERFORMANCE
LATENCY
62 ms of 100 ms
RAM
27 kB of 128 kB
ROM
72 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

2000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)

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

98%
spectr-conv1d-81a
PERFORMANCE
LATENCY
151 ms of 100 ms
Exceeds target by 51 ms
RAM
44 kB of 128 kB
ROM
169 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

2000 ms |
2000 ms |
Enabled

SPECTROGRAM

0.05 | 0.025 | -32

ACCURACY (KERAS)

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

96%
mfcc-conv2d-6f8
PERFORMANCE
LATENCY
191 ms of 100 ms
Exceeds target by 91 ms
RAM
35 kB of 128 kB
ROM
74 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFCC

0.032 | 0.016 | 40

ACCURACY (KERAS)

7/28/2021, 1:52:43 PM

95%
mfcc-conv2d-2eb
PERFORMANCE
LATENCY
151 ms of 100 ms
Exceeds target by 51 ms
RAM
29 kB of 128 kB
ROM
67 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFCC

0.05 | 0.025 | 40

ACCURACY (KERAS)

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

94%
spectr-conv2d-2bf
PERFORMANCE
LATENCY
203 ms of 100 ms
Exceeds target by 103 ms
RAM
25 kB of 128 kB
ROM
101 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.075 | 0.075 | -32

ACCURACY (KERAS)

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