This repository contains a U-Shaped Neural Network(U-Net) model trained on the Pedestrian Dataset for Image Segmentation. The model has achieved an IoU of 78% on the test dataset and is available for use as a Keras model.

Model Details

Architecture: U-Shaped Neural Network (U-Net)
Input Size: Varying Size resized to 128x32 pixels with 1 channel (grayscale)
Data Preprocessing: The model has been trained on normalized data.
IoU: 78%

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

Image Segmentation

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support