Demo Team / Few Shot KWS (Call 911!) 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

Keyword spotting

TI LAUNCHXL-CC1352P (Cortex-M4F 48MHz)

200 ms

80 kB

352 kB

Filters

Status

DSP type

Network type

View

Data set

Precision

Sort

General

F1-score

Precision

Recall

97%
mfe-conv1d-939
Show logs
PERFORMANCE
LATENCY
362 ms of 200 ms
Exceeds target by 162 ms
RAM
25 kB of 80 kB
ROM
46 kB of 352 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
Data augmentation
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
dropout - - 0.5

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

96%
mfe-conv2d-7f0
Show logs
PERFORMANCE
LATENCY
1206 ms of 200 ms
Exceeds target by 1006 ms
RAM
24 kB of 80 kB
ROM
48 kB of 352 kB
DSP NN Unused
INPUT

1000 ms | 250 ms

MFE

0.05 | 0.05 | 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 - - 0.25

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

96%
mfe-conv1d-f97
Show logs
PERFORMANCE
LATENCY
55 ms of 200 ms
RAM
33 kB of 80 kB
ROM
127 kB of 352 kB
DSP NN Unused
INPUT

1000 ms | 250 ms

MFE

0.05 | 0.025 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

Type Filters Kernel Rate
Data augmentation
conv1d 8 3 -
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.5
dense 64 - -
dropout - - 0.5

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

96%
mfe-conv1d-14f
Show logs
PERFORMANCE
LATENCY
203 ms of 200 ms
Exceeds target by 3 ms
RAM
27 kB of 80 kB
ROM
46 kB of 352 kB
DSP NN Unused
INPUT

1000 ms | 250 ms

MFE

0.02 | 0.02 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

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

94%
mfe-conv1d-b7c
Show logs
PERFORMANCE
LATENCY
117 ms of 200 ms
RAM
25 kB of 80 kB
ROM
58 kB of 352 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

MFE

0.05 | 0.025 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

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

94%
mfe-conv1d-a7f
Show logs
PERFORMANCE
LATENCY
312 ms of 200 ms
Exceeds target by 112 ms
RAM
25 kB of 80 kB
ROM
46 kB of 352 kB
DSP NN Unused
INPUT

1000 ms | 250 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 - - 0.5
dense 64 - -
dropout - - 0.5

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

93%
mfe-conv2d-08e
Show logs
PERFORMANCE
LATENCY
1527 ms of 200 ms
Exceeds target by 1327 ms
RAM
21 kB of 80 kB
ROM
45 kB of 352 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

MFE

0.05 | 0.05 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

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

93%
mfe-conv1d-97d
Show logs
PERFORMANCE
LATENCY
205 ms of 200 ms
Exceeds target by 5 ms
RAM
27 kB of 80 kB
ROM
74 kB of 352 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

MFE

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 - - 0.5
dense 64 - -
dropout - - 0.5

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

93%
mfe-conv1d-b27
Show logs
PERFORMANCE
LATENCY
21 ms of 200 ms
RAM
23 kB of 80 kB
ROM
46 kB of 352 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

MFE

0.05 | 0.05 | 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

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

91%
mfe-conv1d-a3f
Show logs
PERFORMANCE
LATENCY
19 ms of 200 ms
RAM
20 kB of 80 kB
ROM
38 kB of 352 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

MFE

0.05 | 0.05 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

Type Filters Kernel Rate
Data augmentation
conv1d 16 3 -
conv1d 32 3 -
dropout - - 0.5

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

91%
mfe-conv1d-b55
Show logs
PERFORMANCE
LATENCY
44 ms of 200 ms
RAM
24 kB of 80 kB
ROM
38 kB of 352 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
conv1d 16 3 -
conv1d 32 3 -
dropout - - 0.25

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

90%
mfe-conv1d-e60
Show logs
PERFORMANCE
LATENCY
761 ms of 200 ms
Exceeds target by 561 ms
RAM
25 kB of 80 kB
ROM
85 kB of 352 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

MFE

0.05 | 0.025 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

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

90%
mfe-conv2d-47f
Show logs
PERFORMANCE
LATENCY
105 ms of 200 ms
RAM
25 kB of 80 kB
ROM
36 kB of 352 kB
DSP NN Unused
INPUT

1000 ms | 250 ms

MFE

0.05 | 0.05 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

Type Filters Kernel Rate
conv2d 8 3 -
conv2d 16 3 -
dropout - - 0.5

4/5/2022, 2:31:07 PM

90%
mfe-conv1d-c22
Show logs
PERFORMANCE
LATENCY
41 ms of 200 ms
RAM
22 kB of 80 kB
ROM
46 kB of 352 kB
DSP NN Unused
INPUT

1000 ms | 500 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 -
dropout - - 0.25

4/5/2022, 2:17:43 PM

90%
mfe-conv2d-35c
Show logs
PERFORMANCE
LATENCY
227 ms of 200 ms
Exceeds target by 27 ms
RAM
22 kB of 80 kB
ROM
46 kB of 352 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

MFE

0.05 | 0.05 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

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

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