David Schwarz / Acoustic Anomaly Detection - TI LaunchPad 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-af0
PERFORMANCE
LATENCY
93 ms of 100 ms
RAM
48 kB of 128 kB
ROM
683 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

2000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)

10/21/2021, 2:40:04 PM

100%
mfe-conv1d-c1f
PERFORMANCE
LATENCY
122 ms of 100 ms
Exceeds target by 22 ms
RAM
49 kB of 128 kB
ROM
156 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

2000 ms |
2000 ms |
Enabled

MFE

0.032 | 0.032 | 40

ACCURACY (KERAS)

10/21/2021, 2:40:09 PM

100%
mfe-conv1d-19a
PERFORMANCE
LATENCY
139 ms of 100 ms
Exceeds target by 39 ms
RAM
36 kB of 128 kB
ROM
75 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

2000 ms |
2000 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)

10/21/2021, 2:45:47 PM

99%
mfe-conv1d-1e9
PERFORMANCE
LATENCY
93 ms of 100 ms
RAM
40 kB of 128 kB
ROM
87 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

2000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)

10/21/2021, 2:53:16 PM

97%
spectr-conv1d-c3f
PERFORMANCE
LATENCY
101 ms of 100 ms
Exceeds target by 1 ms
RAM
28 kB of 128 kB
ROM
75 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

SPECTROGRAM

0.075 | 0.0375 | -52

ACCURACY (KERAS)

10/21/2021, 2:46:03 PM

97%
spectr-conv1d-8cf
PERFORMANCE
LATENCY
103 ms of 100 ms
Exceeds target by 3 ms
RAM
16 kB of 128 kB
ROM
44 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

SPECTROGRAM

0.025 | 0.025 | -72

ACCURACY (KERAS)

10/21/2021, 2:53:26 PM

96%
spectr-conv1d-42d
PERFORMANCE
LATENCY
153 ms of 100 ms
Exceeds target by 53 ms
RAM
20 kB of 128 kB
ROM
75 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

SPECTROGRAM

0.025 | 0.025 | -52

ACCURACY (KERAS)

10/21/2021, 2:45:56 PM

96%
mfe-conv1d-d5e
PERFORMANCE
LATENCY
62 ms of 100 ms
RAM
27 kB of 128 kB
ROM
88 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFE

0.032 | 0.032 | 40

ACCURACY (KERAS)

10/21/2021, 2:50:49 PM

95%
mfe-conv1d-c65
PERFORMANCE
LATENCY
41 ms of 100 ms
RAM
28 kB of 128 kB
ROM
45 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
250 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)

10/21/2021, 2:49:03 PM

93%
mfe-conv1d-978
PERFORMANCE
LATENCY
27 ms of 100 ms
RAM
26 kB of 128 kB
ROM
38 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
250 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)

10/21/2021, 2:51:51 PM

93%
spectr-conv1d-fa5
PERFORMANCE
LATENCY
150 ms of 100 ms
Exceeds target by 50 ms
RAM
20 kB of 128 kB
ROM
43 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

SPECTROGRAM

0.05 | 0.05 | -52

ACCURACY (KERAS)

10/21/2021, 2:50:57 PM

93%
spectr-conv1d-b78
PERFORMANCE
LATENCY
103 ms of 100 ms
Exceeds target by 3 ms
RAM
19 kB of 128 kB
ROM
45 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
250 ms |
Enabled

SPECTROGRAM

0.025 | 0.025 | -32

ACCURACY (KERAS)

10/21/2021, 2:49:00 PM

92%
spectr-conv1d-34d
PERFORMANCE
LATENCY
103 ms of 100 ms
Exceeds target by 3 ms
RAM
19 kB of 128 kB
ROM
45 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
250 ms |
Enabled

SPECTROGRAM

0.025 | 0.025 | -32

ACCURACY (KERAS)

10/21/2021, 2:48:50 PM

92%
mfe-conv1d-5d6
PERFORMANCE
LATENCY
122 ms of 100 ms
Exceeds target by 22 ms
RAM
36 kB of 128 kB
ROM
329 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFE

0.032 | 0.016 | 40

ACCURACY (KERAS)

10/21/2021, 2:45:17 PM

92%
spectr-conv1d-f8a
PERFORMANCE
LATENCY
39 ms of 100 ms
RAM
19 kB of 128 kB
ROM
39 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
250 ms |
Enabled

SPECTROGRAM

0.025 | 0.025 | -32

ACCURACY (KERAS)

10/21/2021, 2:39:56 PM