Nekhil R / Accident reporting by Keyword spotting 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

Cortex-M7 216MHz

100 ms

340 kB

1024 kB

Filters

Status

DSP type

Network type

View

Data set

Precision

Sort

General

F1-score

Precision

Recall

mfe-conv1d-d25
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
INPUT

1000 ms | 1000 ms

MFE

0.02 | 0.01 | 32

ACCURACY
CLASSIFICATION

0.005 | 100

Type Filters Kernel Rate
conv1d 16 3 -
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
dropout - - 0.25

mfcc-conv2d-14f
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
INPUT

1000 ms | 1000 ms

MFCC

0.032 | 0.016 | 40

ACCURACY
CLASSIFICATION

0.005 | 100

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

mfe-conv1d-743
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
INPUT

1000 ms | 1000 ms

MFE

0.02 | 0.01 | 32

ACCURACY
CLASSIFICATION

0.005 | 100

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

mfe-mobilenetv1-5e5
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
INPUT

1000 ms | 500 ms

MFE

0.02 | 0.01 | 40

ACCURACY
TRANSFER LEARNING (KEYWORD SPOTTING)

0.01 | 30

MobileNetV1 0.1
128 | 0.1

mfe-conv2d-570
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
INPUT

1000 ms | 1000 ms

MFE

0.032 | 0.016 | 32

ACCURACY
CLASSIFICATION

0.005 | 100

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

mfcc-conv2d-268
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
INPUT

1000 ms | 1000 ms

MFCC

0.032 | 0.032 | 32

ACCURACY
CLASSIFICATION

0.005 | 100

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

mfcc-conv2d-7b5
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
INPUT

1000 ms | 1000 ms

MFCC

0.02 | 0.02 | 32

ACCURACY
CLASSIFICATION

0.005 | 100

Type Filters Kernel Rate
conv2d 16 3 -
conv2d 32 3 -
dropout - - 0.25

mfcc-conv1d-d3e
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
INPUT

1000 ms | 1000 ms

MFCC

0.02 | 0.02 | 40

ACCURACY
CLASSIFICATION

0.005 | 100

Type Filters Kernel Rate
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
conv1d 256 3 -
dropout - - 0.5

mfe-conv1d-fb8
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
INPUT

1000 ms | 1000 ms

MFE

0.02 | 0.01 | 32

ACCURACY
CLASSIFICATION

0.005 | 100

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

mfe-conv1d-41e
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
INPUT

1000 ms | 1000 ms

MFE

0.02 | 0.01 | 32

ACCURACY
CLASSIFICATION

0.005 | 100

Type Filters Kernel Rate
conv1d 32 3 -
conv1d 64 3 -
dropout - - 0.25

mfcc-conv2d-b96
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
INPUT

1000 ms | 1000 ms

MFCC

0.032 | 0.032 | 32

ACCURACY
CLASSIFICATION

0.005 | 100

Type Filters Kernel Rate
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
conv2d 128 3 -
dropout - - 0.5

mfcc-conv2d-a5b
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
INPUT

1000 ms | 1000 ms

MFCC

0.032 | 0.016 | 40

ACCURACY
CLASSIFICATION

0.005 | 100

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

mfcc-conv2d-cc0
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
INPUT

1000 ms | 1000 ms

MFCC

0.05 | 0.025 | 32

ACCURACY
CLASSIFICATION

0.005 | 100

Type Filters Kernel Rate
conv2d 16 3 -
conv2d 32 3 -
conv2d 64 3 -
conv2d 128 3 -
dropout - - 0.25

mfe-conv2d-fe4
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
INPUT

1000 ms | 1000 ms

MFE

0.05 | 0.05 | 32

ACCURACY
CLASSIFICATION

0.005 | 100

Type Filters Kernel Rate
conv2d 32 3 -
conv2d 64 3 -
dropout - - 0.5

mfe-conv1d-043
PERFORMANCE
LATENCY
100 ms
RAM
340 kB
ROM
1024 kB
Unused
INPUT

1000 ms | 1000 ms

MFE

0.02 | 0.01 | 32

ACCURACY
CLASSIFICATION

0.005 | 100

Type Filters Kernel Rate
Data augmentation
conv1d 32 3 -
conv1d 64 3 -
conv1d 128 3 -
dropout - - 0.25

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