Hui / MelanomaCancerDetection_TansferLearning Public

Target: Arduino Nano 33 BLE Sense (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.

MelanomaCancerDetection_TansferLearning

Images

About this project

Melanoma is a type of cancer that can be deadly if not detected early. It accounts for 75% of skin cancer deaths.This project shows how to use Edge impulse platform for creating a machine learning model to run it on mobile phones and Edge devices such as Arduino Nano 33 Ble.we use the ISIC Skin Cancer dataset ( https://isic-archive.com/).

Data (10,584 items)

View all

melanoma_134

ID: 520619047

Label: benign

melanoma_491

ID: 520618653

Label: benign

melanoma_4756

ID: 520613636

Label: benign

melanoma_9360

ID: 520607305

Label: malignant

melanoma_3098

ID: 520615710

Label: benign

melanoma_6923

ID: 520610718

Label: malignant

melanoma_4763

ID: 520613619

Label: benign

melanoma_7064

ID: 520610501

Label: malignant

Model accuracy (Unoptimized (float32))

Validation set

90.7%

Test set

86.2%

On-device performance (Arduino Nano 33 BLE Sense (Cortex-M4F 64MHz), Quantized (int8))

Latency

1958 ms.

Peak RAM usage

333.8K

Flash usage

579.7K

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

10,584 items

Labels

benign, malignant

Project info

Project ID	246914
Project version	1
License	Apache 2.0
No. of views	14,091
No. of clones	0