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
Sony Spresense (Cortex-M4F 156MHz)
100 ms
1536 kB
8096 kB
Filters
Status
DSP type
Model type
View
Data set
Variant
Sort
General
F1-score
Precision
Recall
75%
rgb-mobilenetv2-96d
PERFORMANCE
LATENCY
3451 ms of 100 ms
Exceeds target by 3351 ms
RAM
738 kB of 1536 kB
ROM
586 kB of 8096 kB
DSP NN Unused
IMAGE INPUT
160 |
160
IMAGE
RGB
ACCURACY (KERAS-TRANSFER-IMAGE)
1/11/2022, 6:46:08 AM
75%
grayscale-mobilenetv1-50a
PERFORMANCE
LATENCY
660 ms of 100 ms
Exceeds target by 560 ms
RAM
135 kB of 1536 kB
ROM
312 kB of 8096 kB
DSP NN Unused
IMAGE INPUT
96 |
96
IMAGE
Grayscale
ACCURACY (KERAS-TRANSFER-IMAGE)
1/11/2022, 6:35:12 AM
20%
rgb-conv2d-caa
PERFORMANCE
LATENCY
18926 ms of 100 ms
Exceeds target by 18826 ms
RAM
369 kB of 1536 kB
ROM
2358 kB of 8096 kB
DSP NN Unused
IMAGE INPUT
96 |
96
IMAGE
RGB
ACCURACY (KERAS)
1/11/2022, 6:48:20 AM
rgb-conv2d-344
PERFORMANCE
LATENCY
147 ms of 100 ms
Exceeds target by 47 ms
RAM
30 kB of 1536 kB
ROM
122 kB of 8096 kB
DSP NN Unused
IMAGE INPUT
32 |
32
IMAGE
RGB
ACCURACY (KERAS)
1/11/2022, 6:27:32 AM
80%
rgb-conv2d-67d
PERFORMANCE
LATENCY
2327 ms of 100 ms
Exceeds target by 2227 ms
RAM
369 kB of 1536 kB
ROM
2358 kB of 8096 kB
DSP NN Unused
IMAGE INPUT
96 |
96
IMAGE
RGB
ACCURACY (KERAS)
1/11/2022, 6:52:02 AM
75%
grayscale-mobilenetv2-567
PERFORMANCE
LATENCY
1342 ms of 100 ms
Exceeds target by 1242 ms
RAM
351 kB of 1536 kB
ROM
586 kB of 8096 kB
DSP NN Unused
IMAGE INPUT
96 |
96
IMAGE
Grayscale
ACCURACY (KERAS-TRANSFER-IMAGE)
1/11/2022, 6:46:20 AM
75%
grayscale-mobilenetv1-c1f
PERFORMANCE
LATENCY
406 ms of 100 ms
Exceeds target by 306 ms
RAM
64 kB of 1536 kB
ROM
110 kB of 8096 kB
DSP NN Unused
IMAGE INPUT
96 |
96
IMAGE
Grayscale
ACCURACY (KERAS-TRANSFER-IMAGE)
1/11/2022, 6:52:39 AM
75%
grayscale-mobilenetv1-7fc
PERFORMANCE
LATENCY
685 ms of 100 ms
Exceeds target by 585 ms
RAM
111 kB of 1536 kB
ROM
228 kB of 8096 kB
DSP NN Unused
IMAGE INPUT
96 |
96
IMAGE
Grayscale
ACCURACY (KERAS-TRANSFER-IMAGE)
1/11/2022, 6:55:17 AM
75%
grayscale-mobilenetv1-d71
PERFORMANCE
LATENCY
532 ms of 100 ms
Exceeds target by 432 ms
RAM
111 kB of 1536 kB
ROM
228 kB of 8096 kB
DSP NN Unused
IMAGE INPUT
96 |
96
IMAGE
Grayscale
ACCURACY (KERAS-TRANSFER-IMAGE)
1/11/2022, 6:59:42 AM
75%
rgb-mobilenetv2-e8b
PERFORMANCE
LATENCY
600 ms of 100 ms
Exceeds target by 500 ms
RAM
965 kB of 1536 kB
ROM
1652 kB of 8096 kB
DSP NN Unused
IMAGE INPUT
96 |
96
IMAGE
RGB
ACCURACY (KERAS-TRANSFER-IMAGE)
1/11/2022, 7:02:48 AM
rgb-mobilenetv2-7cd
PERFORMANCE
LATENCY
100 ms
RAM
1536 kB
ROM
8096 kB
Unused
IMAGE INPUT
160 |
160
IMAGE
RGB
ACCURACY (KERAS-TRANSFER-IMAGE)
grayscale-conv2d-b1f
PERFORMANCE
LATENCY
100 ms
RAM
1536 kB
ROM
8096 kB
Unused
IMAGE INPUT
96 |
96
IMAGE
Grayscale
ACCURACY (KERAS)
rgb-mobilenetv2-f40
PERFORMANCE
LATENCY
100 ms
RAM
1536 kB
ROM
8096 kB
Unused
IMAGE INPUT
96 |
96
IMAGE
RGB
ACCURACY (KERAS-TRANSFER-IMAGE)
grayscale-mobilenetv1-77b
PERFORMANCE
LATENCY
100 ms
RAM
1536 kB
ROM
8096 kB
Unused
IMAGE INPUT
96 |
96
IMAGE
Grayscale
ACCURACY (KERAS-TRANSFER-IMAGE)
grayscale-mobilenetv2-768
PERFORMANCE
LATENCY
100 ms
RAM
1536 kB
ROM
8096 kB
Unused
IMAGE INPUT
96 |
96
IMAGE
Grayscale
ACCURACY (KERAS-TRANSFER-IMAGE)
Training output
Hide
Click 'Run EON Tuner' to begin
