Nicholas Chiapputo / audio-rslk-control 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

100%
mfcc-conv1d-423
Show logs
PERFORMANCE
LATENCY
6 ms of 200 ms
RAM
51 kB of 80 kB
ROM
132 kB of 352 kB
DSP NN Unused
INPUT

1000 ms | 500 ms

MFCC

0.05 | 0.05 | 40

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

1/10/2022, 8:50:47 AM

100%
mfe-conv2d-d3e
Show logs
PERFORMANCE
LATENCY
157 ms of 200 ms
RAM
28 kB of 80 kB
ROM
60 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
conv2d 8 3 -
conv2d 16 3 -
conv2d 32 3 -
dropout - - 0.5

1/10/2022, 8:51:06 AM

100%
mfe-conv1d-f9c
Show logs
PERFORMANCE
LATENCY
72 ms of 200 ms
RAM
53 kB of 80 kB
ROM
132 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
conv1d 16 3 -
conv1d 32 3 -
dropout - - 0.25

1/10/2022, 8:50:50 AM

100%
mfcc-conv1d-f12
Show logs
PERFORMANCE
LATENCY
24 ms of 200 ms
RAM
19 kB of 80 kB
ROM
34 kB of 352 kB
DSP NN Unused
INPUT

1000 ms | 250 ms

MFCC

0.032 | 0.032 | 32

ACCURACY
NEURAL NETWORK (KERAS)

0.005 | 100

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

1/10/2022, 8:54:21 AM

100%
mfe-conv2d-92a
Show logs
PERFORMANCE
LATENCY
284 ms of 200 ms
Exceeds target by 84 ms
RAM
28 kB of 80 kB
ROM
60 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 -
conv2d 64 3 -
dropout - - 0.5

1/10/2022, 8:51:11 AM

100%
mfcc-conv1d-58f
Show logs
PERFORMANCE
LATENCY
11 ms of 200 ms
RAM
5 kB of 80 kB
ROM
47 kB of 352 kB
DSP NN Unused
INPUT

1000 ms | 250 ms

MFCC

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 - - 0.25
dense 64 - -
dropout - - 0.25

1/10/2022, 8:53:50 AM

100%
mfe-conv1d-49c
Show logs
PERFORMANCE
LATENCY
104 ms of 200 ms
RAM
29 kB of 80 kB
ROM
73 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 16 3 -
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
dropout - - 0.5

1/10/2022, 8:53:21 AM

100%
mfcc-conv1d-66c
Show logs
PERFORMANCE
LATENCY
17 ms of 200 ms
RAM
27 kB of 80 kB
ROM
73 kB of 352 kB
DSP NN Unused
INPUT

1000 ms | 1000 ms

MFCC

0.05 | 0.05 | 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

1/10/2022, 8:53:17 AM

100%
mfe-conv1d-ec9
Show logs
PERFORMANCE
LATENCY
22 ms of 200 ms
RAM
5 kB of 80 kB
ROM
47 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
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.25

1/10/2022, 8:53:28 AM

100%
mfe-conv2d-4b0
Show logs
PERFORMANCE
LATENCY
962 ms of 200 ms
Exceeds target by 762 ms
RAM
26 kB of 80 kB
ROM
41 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
conv2d 8 3 -
conv2d 16 3 -
dropout - - 0.5

1/10/2022, 8:50:58 AM

100%
mfe-conv1d-e12
Show logs
PERFORMANCE
LATENCY
46 ms of 200 ms
RAM
25 kB of 80 kB
ROM
89 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 -
conv1d 128 3 -
dropout - - 0.5
dense 64 - -
dropout - - 0.5

1/10/2022, 8:52:08 AM

100%
mfe-conv1d-aa9
Show logs
PERFORMANCE
LATENCY
133 ms of 200 ms
RAM
17 kB of 80 kB
ROM
0 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 32 3 -
conv1d 64 3 -
dropout - - 0.5
dense 64 - -
dropout - - 0.5

1/10/2022, 8:51:51 AM

100%
mfe-conv1d-6ee
Show logs
PERFORMANCE
LATENCY
64 ms of 200 ms
RAM
28 kB of 80 kB
ROM
89 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
Data augmentation
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.5

1/10/2022, 8:52:04 AM

100%
mfe-conv1d-28b
Show logs
PERFORMANCE
LATENCY
67 ms of 200 ms
RAM
22 kB of 80 kB
ROM
58 kB of 352 kB
DSP NN Unused
INPUT

1000 ms | 500 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

1/10/2022, 8:52:22 AM

100%
mfe-conv1d-b38
Show logs
PERFORMANCE
LATENCY
28 ms of 200 ms
RAM
12 kB of 80 kB
ROM
191 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 8 3 -
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.5
dense 64 - -
dropout - - 0.5

1/10/2022, 8:54:37 AM

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