Toolwear-Detection is a Python-based project designed to detect tool wear using machine learning techniques. The project categorizes tool wear with an accuracy of 83.33% into fine, mild, and severe classes.
- Data Transformation: Preprocess images with resizing, normalization, and augmentation.
- Model Configuration: Modify a pre-trained GoogLeNet, resnet model to classify tool wear into three categories.
- Classification: Use the trained model to predict the class label of each image.
-
GoogLeNet: Utilizes a pre-trained GoogLeNet model, fine-tuned for tool wear detection.
-
Custom Classifier: Replaces the final fully connected layer to output three class probabilities.
-
Training and Evaluation: Trained with cross-entropy loss and evaluated based on accuracy, precision, recall, and F1 score.
To use the tool wear detection algorithm, follow these steps:
- Clone the repository:
git clone https://github.com/aryanpola/Toolwear-Detection.git
- Navigate to the project directory:
cd Toolwear-Detection - Install Dependencies:
pip install -r requirements.txt
- Run the main script:
python main.py
This project is licensed under the MIT License. See the LICENSE file for details.
Contributions are welcome! Please feel free to submit a pull request or open an issue.
Special thanks to all contributors and the open-source community for their invaluable support and contributions.
For any inquiries or support, please contact me at [email protected].