Datasets by Edge Impulse / Image Classification - Fire extinguisher safety pin Public
Target: Cortex-M7 216MHz 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

Cortex-M7 216MHz

100 ms

340 kB

1024 kB

Filters

Status

DSP type

Model type

View

Data set

Variant

Sort

General

F1-score

Precision

Recall

81%
rgb-conv2d-743
Show logs
PERFORMANCE
LATENCY
52 ms of 100 ms
RAM
281 kB of 340 kB
ROM
106 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 10 | 81%

Type Filters Kernel Rate
conv2d 8 3 -
conv2d 16 3 -
dropout - - 0.5

7/23/2024, 2:16:46 PM

81%
rgb-conv2d-2e9
Show logs
PERFORMANCE
LATENCY
90 ms of 100 ms
RAM
185 kB of 340 kB
ROM
68 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

128 |
128

IMAGE

RGB

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 10 | 81%

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

7/23/2024, 2:07:33 PM

74%
rgb-conv2d-056
Show logs
PERFORMANCE
LATENCY
58 ms of 100 ms
RAM
281 kB of 340 kB
ROM
106 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 10 | 74%

Type Filters Kernel Rate
conv2d 8 3 -
conv2d 16 3 -
dropout - - 0.25

7/23/2024, 2:22:26 PM

74%
rgb-conv2d-b1d
Show logs
PERFORMANCE
LATENCY
72 ms of 100 ms
RAM
282 kB of 340 kB
ROM
74 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 10 | 74%

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

7/23/2024, 2:17:48 PM

72%
rgb-mobilenetv2-5fd
Show logs
PERFORMANCE
LATENCY
822 ms of 100 ms
Exceeds target by 722 ms
RAM
1491 kB of 340 kB
Exceeds target by 1151 kB
ROM
2611 kB of 1024 kB
Exceeds target by 1587 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

RGB

ACCURACY (KERAS-TRANSFER-IMAGE)
TRANSFER LEARNING (IMAGES)

0.0005 | 20 | 72%

MobileNetV2 160x160 1.0
64 | 0.1 |

7/23/2024, 2:12:44 PM

rgb-conv2d-fab
Show logs
PERFORMANCE
LATENCY
61 ms of 100 ms
RAM
92 kB of 340 kB
ROM
136 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

64 |
64

IMAGE

RGB

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 10 | 0%

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

7/23/2024, 2:10:27 PM

grayscale-conv2d-4ba
Show logs
PERFORMANCE
LATENCY
105 ms of 100 ms
Exceeds target by 5 ms
RAM
92 kB of 340 kB
ROM
135 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

64 |
64

IMAGE

Grayscale

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 10 | 0%

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

7/23/2024, 2:09:35 PM

grayscale-conv2d-5f2
Show logs
PERFORMANCE
LATENCY
126 ms of 100 ms
Exceeds target by 26 ms
RAM
257 kB of 340 kB
ROM
74 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

Grayscale

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 10 | 0%

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

7/23/2024, 2:10:25 PM

grayscale-conv2d-513
Show logs
PERFORMANCE
LATENCY
138 ms of 100 ms
Exceeds target by 38 ms
RAM
259 kB of 340 kB
ROM
75 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

160 |
160

IMAGE

Grayscale

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 10 | 0%

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

7/23/2024, 2:09:33 PM

grayscale-conv2d-3bc
Show logs
PERFORMANCE
LATENCY
115 ms of 100 ms
Exceeds target by 15 ms
RAM
327 kB of 340 kB
ROM
131 kB of 1024 kB
DSP NN Unused
IMAGE INPUT

128 |
128

IMAGE

Grayscale

ACCURACY (KERAS)
CLASSIFICATION

0.0005 | 10 | 0%

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

7/23/2024, 2:08:07 PM

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