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
Run #1 (Feb 24 2024, 11:17:18, finished)
100%
rgb-ssd-664
PERFORMANCE
LATENCY
349207 ms of 100 ms
Exceeds target by 349107 ms
RAM
4 kB of 4096 kB
ROM
11232 kB of 4096 kB
Exceeds target by 7136 kB
DSP NN Unused
IMAGE INPUT
320 |
320
IMAGE
RGB
OBJECT DETECTION (IMAGES)
0.01 | 30 | 100%
MobileNetV2 SSD FPN-Lite | float32
2/24/2024, 11:33:23 AM
100%
rgb-ssd-d74
PERFORMANCE
LATENCY
323216 ms of 100 ms
Exceeds target by 323116 ms
RAM
4 kB of 4096 kB
ROM
11232 kB of 4096 kB
Exceeds target by 7136 kB
DSP NN Unused
IMAGE INPUT
320 |
320
IMAGE
RGB
OBJECT DETECTION (IMAGES)
0.01 | 60 | 100%
MobileNetV2 SSD FPN-Lite | float32
2/24/2024, 11:27:26 AM
10%
rgb-ssd-8f3
PERFORMANCE
LATENCY
292699 ms of 100 ms
Exceeds target by 292599 ms
RAM
4 kB of 4096 kB
ROM
11232 kB of 4096 kB
Exceeds target by 7136 kB
DSP NN Unused
IMAGE INPUT
320 |
320
IMAGE
RGB
OBJECT DETECTION (IMAGES)
0.001 | 60 | 10%
MobileNetV2 SSD FPN-Lite | float32
2/24/2024, 11:35:36 AM
10%
rgb-ssd-c65
PERFORMANCE
LATENCY
345460 ms of 100 ms
Exceeds target by 345360 ms
RAM
4 kB of 4096 kB
ROM
11232 kB of 4096 kB
Exceeds target by 7136 kB
DSP NN Unused
IMAGE INPUT
320 |
320
IMAGE
RGB
OBJECT DETECTION (IMAGES)
0.001 | 30 | 10%
MobileNetV2 SSD FPN-Lite | float32
2/24/2024, 11:25:29 AM
Training output
Hide
Click 'Run EON Tuner' to begin
