Demo Team / Few Shot KWS (Call 911!) 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

TI LAUNCHXL-CC1352P (Cortex-M4F 48MHz)

100 ms

80 kB

352 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

99%
mfe-conv2d-08e
PERFORMANCE
LATENCY
1527 ms of 100 ms
Exceeds target by 1427 ms
RAM
21 kB of 80 kB
ROM
45 kB of 352 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)

4/5/2022, 2:28:13 PM

99%
mfe-conv1d-97d
PERFORMANCE
LATENCY
205 ms of 100 ms
Exceeds target by 105 ms
RAM
27 kB of 80 kB
ROM
74 kB of 352 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFE

0.02 | 0.02 | 40

ACCURACY (KERAS)

4/5/2022, 2:25:34 PM

99%
mfe-conv2d-7f0
PERFORMANCE
LATENCY
1206 ms of 100 ms
Exceeds target by 1106 ms
RAM
24 kB of 80 kB
ROM
48 kB of 352 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
250 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)

4/5/2022, 2:23:54 PM

97%
mfe-conv1d-b27
PERFORMANCE
LATENCY
21 ms of 100 ms
RAM
23 kB of 80 kB
ROM
46 kB of 352 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)

4/5/2022, 2:24:50 PM

97%
mfe-conv1d-f97
PERFORMANCE
LATENCY
55 ms of 100 ms
RAM
33 kB of 80 kB
ROM
127 kB of 352 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
250 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)

4/5/2022, 2:21:42 PM

97%
mfe-conv1d-a7f
PERFORMANCE
LATENCY
312 ms of 100 ms
Exceeds target by 212 ms
RAM
25 kB of 80 kB
ROM
46 kB of 352 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
250 ms |
Enabled

MFE

0.032 | 0.032 | 40

ACCURACY (KERAS)

4/5/2022, 2:20:41 PM

97%
mfe-conv1d-939
PERFORMANCE
LATENCY
362 ms of 100 ms
Exceeds target by 262 ms
RAM
25 kB of 80 kB
ROM
46 kB of 352 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)

4/5/2022, 2:17:34 PM

96%
mfe-conv1d-b7c
PERFORMANCE
LATENCY
117 ms of 100 ms
Exceeds target by 17 ms
RAM
25 kB of 80 kB
ROM
58 kB of 352 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)

4/5/2022, 2:22:08 PM

96%
mfe-conv1d-14f
PERFORMANCE
LATENCY
203 ms of 100 ms
Exceeds target by 103 ms
RAM
27 kB of 80 kB
ROM
46 kB of 352 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
250 ms |
Enabled

MFE

0.02 | 0.02 | 40

ACCURACY (KERAS)

4/5/2022, 2:20:37 PM

94%
mfe-conv1d-a3f
PERFORMANCE
LATENCY
19 ms of 100 ms
RAM
20 kB of 80 kB
ROM
38 kB of 352 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)

4/5/2022, 2:24:14 PM

94%
mfe-conv2d-35c
PERFORMANCE
LATENCY
227 ms of 100 ms
Exceeds target by 127 ms
RAM
22 kB of 80 kB
ROM
46 kB of 352 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)

4/5/2022, 2:17:39 PM

93%
mfe-conv1d-e60
PERFORMANCE
LATENCY
761 ms of 100 ms
Exceeds target by 661 ms
RAM
25 kB of 80 kB
ROM
85 kB of 352 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)

4/5/2022, 2:20:08 PM

93%
mfe-conv2d-68b
PERFORMANCE
LATENCY
195 ms of 100 ms
Exceeds target by 95 ms
RAM
49 kB of 80 kB
ROM
61 kB of 352 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
250 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)

4/5/2022, 2:15:33 PM

91%
mfe-conv1d-b55
PERFORMANCE
LATENCY
44 ms of 100 ms
RAM
24 kB of 80 kB
ROM
38 kB of 352 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

MFE

0.05 | 0.025 | 40

ACCURACY (KERAS)

4/5/2022, 2:22:55 PM

90%
mfe-conv1d-5b6
PERFORMANCE
LATENCY
51 ms of 100 ms
RAM
25 kB of 80 kB
ROM
89 kB of 352 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
250 ms |
Enabled

MFE

0.05 | 0.05 | 40

ACCURACY (KERAS)

4/5/2022, 2:19:11 PM