jenna.su / esp32_fruit Public
Target: Espressif ESP-EYE (ESP32 240MHz) Clone this project
Experiments 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

Espressif ESP-EYE (ESP32 240MHz)

100 ms

4096 kB

4096 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

100%
raw-dense-ec1
Show logs
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
1 kB of 4096 kB
ROM
16 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
1000 ms |
Enabled

RAW

1

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 100%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dropout - - 0.5

5/18/2023, 7:39:14 AM

100%
raw-dense-290
Show logs
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
2 kB of 4096 kB
ROM
16 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
1000 ms |
Enabled

RAW

1

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 100%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dense 10 - -
dropout - - 0.25

5/18/2023, 7:39:09 AM

100%
raw-dense-cf9
Show logs
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
1 kB of 4096 kB
ROM
16 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
2000 ms |
Enabled

RAW

1

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 100%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dropout - - 0.25

5/18/2023, 7:39:34 AM

99%
raw-dense-c0d
Show logs
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
1 kB of 4096 kB
ROM
16 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

2000 ms |
1000 ms |
Enabled

RAW

1

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 99%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dense 10 - -
dropout - - 0.5

5/18/2023, 7:40:07 AM

98%
raw-dense-95a
Show logs
PERFORMANCE
LATENCY
1 ms of 100 ms
RAM
1 kB of 4096 kB
ROM
15 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

2000 ms |
500 ms |
Enabled

RAW

1

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 98%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dropout - - 0.25

5/18/2023, 7:38:06 AM

96%
raw-dense-4b5
Show logs
PERFORMANCE
LATENCY
1 ms of 100 ms
RAM
1 kB of 4096 kB
ROM
15 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
250 ms |
Enabled

RAW

1

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 96%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dropout - - 0.25

5/18/2023, 7:34:39 AM

96%
raw-dense-e4a
Show logs
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
1 kB of 4096 kB
ROM
15 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

RAW

1

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 96%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dropout - - 0.25

5/18/2023, 7:38:12 AM

86%
raw-dense-3f9
Show logs
PERFORMANCE
LATENCY
1 ms of 100 ms
RAM
1 kB of 4096 kB
ROM
14 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
1000 ms |
Enabled

RAW

1

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 86%

Type Filters Kernel Rate
dense 20 - -
dense 10 - -
dropout - - 0.5

5/18/2023, 7:43:35 AM

86%
raw-dense-fc0
Show logs
PERFORMANCE
LATENCY
1 ms of 100 ms
RAM
1 kB of 4096 kB
ROM
14 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

1000 ms |
500 ms |
Enabled

RAW

1

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 86%

Type Filters Kernel Rate
dense 20 - -
dense 10 - -
dropout - - 0.25

5/18/2023, 7:38:45 AM

86%
raw-dense-e59
Show logs
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
1 kB of 4096 kB
ROM
16 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

2000 ms |
500 ms |
Enabled

RAW

1

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 86%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dense 10 - -
dropout - - 0.5

5/18/2023, 7:43:30 AM

84%
raw-dense-722
Show logs
PERFORMANCE
LATENCY
1 ms of 100 ms
RAM
1 kB of 4096 kB
ROM
15 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

2000 ms |
2000 ms |
Enabled

RAW

1

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 84%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dropout - - 0.5

5/18/2023, 7:43:31 AM

75%
raw-dense-d61
Show logs
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
2 kB of 4096 kB
ROM
16 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
4000 ms |
Enabled

RAW

1

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 75%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dense 10 - -
dropout - - 0.25

5/18/2023, 7:33:52 AM

73%
raw-dense-07c
Show logs
PERFORMANCE
LATENCY
2 ms of 100 ms
RAM
1 kB of 4096 kB
ROM
16 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
2000 ms |
Enabled

RAW

1

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 73%

Type Filters Kernel Rate
dense 40 - -
dense 20 - -
dropout - - 0.5

5/18/2023, 7:46:11 AM

58%
raw-dense-786
Show logs
PERFORMANCE
LATENCY
1 ms of 100 ms
RAM
1 kB of 4096 kB
ROM
14 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

2000 ms |
500 ms |
Enabled

RAW

1

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 58%

Type Filters Kernel Rate
dense 20 - -
dense 10 - -
dropout - - 0.25

5/18/2023, 7:43:38 AM

57%
raw-dense-a83
Show logs
PERFORMANCE
LATENCY
1 ms of 100 ms
RAM
1 kB of 4096 kB
ROM
15 kB of 4096 kB
DSP NN Unused
TIME-SERIES INPUT

4000 ms |
1000 ms |
Enabled

RAW

1

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 30 | 57%

Type Filters Kernel Rate
dense 20 - -
dense 10 - -
dropout - - 0.5

5/18/2023, 7:45:01 AM

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