peterchenyipu / imu_mnist3 Public

Target: Nordic nRF52840 DK (Cortex-M4F 64MHz) Clone this project

Welcome to Edge Impulse, the largest community of edge AI developers!
This is a public Edge Impulse project, use the navigation bar to see all data and models in this project; or clone to retrain or deploy to any edge device.

imu_mnist3

MNIST IMU Handwriting Recognition

About this project

This public Edge Impulse project does not have a README yet. Clone this project to add new data or retrain this project, or to deploy this project to a device.

Data (1,656 samples)

View all

8.4s8immd8

ID: 951203351

Label: 8

Sample length: 3s

2.4s3dh18l

ID: 949591477

Label: 2

Sample length: 3s

3.4s3dosp7

ID: 949590012

Label: 3

Sample length: 3s

9.4s8j9mc1

ID: 951227767

Label: 9

Sample length: 3s

0.4s3c7tbl

ID: 949592764

Label: 0

Sample length: 3s

3.4s3dlku9

ID: 949591236

Label: 3

Sample length: 3s

1.4s3csp9m

ID: 949592714

Label: 1

Sample length: 3s

3.4s3dsov7

ID: 949589929

Label: 3

Sample length: 3s

Model accuracy, Time series data, Raw Data, Classification #2 (resnet_large) (Unoptimized (float32))

View 1 other experiment

Validation set

90.8%

Test set

89.4%

On-device performance (Nordic nRF52840 DK (Cortex-M4F 64MHz), Quantized (int8))

Latency

97 ms.

Peak RAM usage

15.2K

Flash usage

57.4K

Run this model

On any device

Clone project

Dataset summary

Data collected

1h 22m 43s

Sensors

ax, ay, az, gx, gy, gz @ 100Hz

Labels

0, 1, 2, 3, 4 and 5 others

Project info

Project ID	386984
License	Apache 2.0
No. of views	15,392
No. of clones	0