Clothing Classification & Instance Segmentation
This repository contains the best-performing models for VR Mini Project 1.
The models are trained on a subset of the DeepFashion2 dataset to recognize 5 clothing categories: short sleeve top, long sleeve top, shorts, trousers, skirt.
Models Included:
- Task 3.1 (Classification): ResNet50 (
cls.pth) - Multi-label image classification. - Task 3.2 (Detection & Segmentation): YOLOv8 (
seg.pt) - Object detection and instance segmentation.
Installation
To run inference, install the required packages:
pip install torch torchvision ultralytics Pillow opencv-python-headless huggingface_hub
- Downloads last month
- 8
# Couldn't find a valid YOLO version tag. # Replace XX with the correct version. from ultralytics import YOLOvXX model = YOLOvXX.from_pretrained("parrvv/Clothing-classification-segmentation") source = 'http://images.cocodataset.org/val2017/000000039769.jpg' model.predict(source=source, save=True)