MS-SE Waste Classifier

MS-SE-EfficientNet-B0

Classify a waste image entirely in your browser.

Upload one image to obtain a ten-class probability distribution. The model uses average, maximum, and standard-deviation channel descriptors with bounded residual attention.

The selected image remains on this device during inference.

Input: 224 × 224 RGB
Classes: 10
Parameters: 4.234M
Runtime: WebAssembly

Step 1

Select an image

Drop an image here or click to browse JPEG, PNG, WebP, or BMP

Step 2

Prediction

WASM

Results will appear here

Load the model, select an image, and press “Classify image.”

Model status

Runtime initialization

Loading ONNX Runtime Web…

Supported classes

Notebook-matched preprocessing

Direct resize to 224 × 224, RGB conversion, scaling to [0,1], and ImageNet normalization.

Research use

Visual ambiguity remains possible, especially among related packaging materials and general trash.