Red Dead Convolution is a deep learning project that uses convolutional neural networks (CNNs) to identify and classify objects from video game Red Dead Redemption 2. This project was designed to explore advanced computer vision techniques in a dynamic, visually rich environment. The code in this repository was contributed to by many members of this project, under the Aggie Coding Club.
- Object Detection: Detects and classifies in-game elements such as animals, plants, NPCs, and weapons.
- Custom Dataset: Utilizes a dataset generated by capturing annotated screenshots from Red Dead Redemption 2.
- Model Training: Employs transfer learning with pretrained models (e.g., ResNet, VGG) to improve accuracy and reduce training time.