Thomas Garcia / keywordspotter_demo 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

93%
mfe-conv1d-380
PERFORMANCE
LATENCY
50 ms of 100 ms
RAM
25 kB of 128 kB
ROM
45 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)

9/28/2021, 5:01:33 PM

92%
mfe-conv1d-5ee
PERFORMANCE
LATENCY
38 ms of 100 ms
RAM
24 kB of 128 kB
ROM
57 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)

9/28/2021, 4:28:46 PM

92%
mfe-conv1d-2f2
PERFORMANCE
LATENCY
38 ms of 100 ms
RAM
27 kB of 128 kB
ROM
75 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)

9/28/2021, 4:44:34 PM

92%
mfe-conv1d-de3
PERFORMANCE
LATENCY
50 ms of 100 ms
RAM
25 kB of 128 kB
ROM
45 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)

9/28/2021, 4:18:48 PM

92%
mfe-conv1d-fcb
PERFORMANCE
LATENCY
26 ms of 100 ms
RAM
21 kB of 128 kB
ROM
44 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
250 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)

9/28/2021, 4:38:47 PM

92%
mfe-conv1d-7bd
PERFORMANCE
LATENCY
26 ms of 100 ms
RAM
21 kB of 128 kB
ROM
44 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)

9/28/2021, 4:23:16 PM

91%
mfe-conv1d-f35
PERFORMANCE
LATENCY
80 ms of 100 ms
RAM
24 kB of 128 kB
ROM
46 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)

9/28/2021, 5:04:50 PM

91%
mfe-conv1d-8a3
PERFORMANCE
LATENCY
82 ms of 100 ms
RAM
22 kB of 128 kB
ROM
95 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)

9/28/2021, 4:53:05 PM

91%
mfe-conv1d-20f
PERFORMANCE
LATENCY
82 ms of 100 ms
RAM
22 kB of 128 kB
ROM
95 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)

9/28/2021, 4:47:11 PM

91%
mfe-conv1d-af6
PERFORMANCE
LATENCY
30 ms of 100 ms
RAM
23 kB of 128 kB
ROM
45 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
250 ms |
Enabled

MFE

0.032 | 0.032 | 40

ACCURACY (KERAS)

9/28/2021, 4:18:37 PM

91%
mfe-conv1d-2b0
PERFORMANCE
LATENCY
80 ms of 100 ms
RAM
29 kB of 128 kB
ROM
265 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
250 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)

9/28/2021, 4:52:33 PM

91%
mfe-conv1d-50a
PERFORMANCE
LATENCY
40 ms of 100 ms
RAM
28 kB of 128 kB
ROM
73 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)

9/28/2021, 4:33:51 PM

91%
mfe-conv1d-8b5
PERFORMANCE
LATENCY
170 ms of 100 ms
Exceeds target by 70 ms
RAM
25 kB of 128 kB
ROM
205 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
250 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)

9/28/2021, 5:07:03 PM

91%
mfe-conv1d-435
PERFORMANCE
LATENCY
32 ms of 100 ms
RAM
24 kB of 128 kB
ROM
37 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)

9/28/2021, 4:43:54 PM

91%
mfe-conv1d-f63
PERFORMANCE
LATENCY
28 ms of 100 ms
RAM
21 kB of 128 kB
ROM
56 kB of 1024 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)

9/28/2021, 4:39:07 PM