Edge Impulse Experts / Adiuvo_BrainChip_VWW Public

Target: BrainChip AKD1000 or AKD1500 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.

Adiuvo_BrainChip_VWW

Images

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 (103,457 items)

View all

COCO_train2014_000000058245

ID: 447369566

Label: non-person

COCO_val2014_000000533678

ID: 447326892

Label: non-person

COCO_train2014_000000390692

ID: 447391907

Label: person

COCO_train2014_000000163579

ID: 447364010

Label: non-person

COCO_val2014_000000532989

ID: 447326933

Label: non-person

COCO_val2014_000000571275

ID: 447320363

Label: person

COCO_val2014_000000476233

ID: 447322649

Label: person

COCO_train2014_000000497797

ID: 447385733

Label: person

Model accuracy, Images, Image, Transfer Learning (Images) - BrainChip Akida™ #5 (vww96) (Unoptimized (float32))

View 5 other experiments

Validation set

85.5%

Test set

80.6%

On-device performance (BrainChip AKD1000 or AKD1500, Unoptimized (float32))

Latency

1854 ms.

Flash usage

882.8K

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

103,457 items

Labels

non-person, person

Project info

Project ID	224143
Project version	2
License	Apache 2.0
No. of views	348,235
No. of clones	8