Fabric Defect Detection is a deep learning project that focuses on identifying and classifying fabric defects using state-of-the-art computer vision techniques. The model is based on the EfficientNetV2 architecture and is trained on a dataset comprising five classes of fabric defects. The goal is to provide an accurate and efficient solution for quality control in textile manufacturing.
Efficient Model: Utilizes EfficientNetV2, a highly efficient and powerful deep learning architecture.
Five-Class Classification: Capable of classifying fabric defects into five distinct categories for comprehensive defect analysis.
Training and Evaluation: Provides scripts for training the model, evaluating its performance, and saving the trained model for future use.
To get started, follow the installation instructions and explore the provided scripts for training, evaluation, and using custom data. The project aims to be user-friendly while delivering robust fabric defect detection capabilities.