Your Website Title
Group_Activity_Recognition

Group Activity Recognition

Group Activity Recognition Table of Contents Key Updates Usage Clone the Repository Install Dependencies Download Model Checkpoint Dataset Overview Example Annotations Train-Test Split Dataset Statistics Dataset Organization Dataset Download Instructions Ablation Study Baselines Performance Comparison Original Paper Baselines Score My Scores (Accuracy and F1 Scores) Interesting Observations Effect of Team Independent Pooling Model Architecture Key Updates ResNet50 for feature extraction (replacing AlexNet). Ablation studies to analyze model components. Implementation of an end-to-end version (Baseline 9). Achieve higher performance across every model baseline compared to the original paper. Full implementation in Python (original used Caffe). Usage 1. Clone the Repository 1 git clone https://github.com/Sh-31/Group-Activity-Recognition.git 2. Install the Required Dependencies 1 pip3 install -r requirements.txt 3. Download the Model Checkpoint This is a manual step that involves downloading the model checkpoint files. ...

February 24, 24240 路 7 min 路 1440 words 路 Sherif Ahmed
ImgCap

ImgCap

Usage Clone the repository: 1 git clone https://github.com/Sh-31/ImgCap.git Install the required dependencies: 1 2 pip3 install -r requirements.txt python3 -q -m spacy download en_core_web_sm Download the model checkpoint (manual step): ImgCap (CNN + LSTM): Download checkpoint ImgCap (CNN + LSTM + Attention): Download checkpoint Place the model checkpoint in the appropriate directory: For CNN + LSTM + Attention: ImgCap/trainning/checkpoints/attention For CNN + LSTM: ImgCap/trainning/checkpoints Run the main script (Gradio GUI for inference): ...

September 10, 10100 路 4 min 路 788 words 路 Sherif Ahmed
ImgCap

Tennis Analysis System

Tennis-Analysis-System Tennis-Analysis-System is a system that analyzes tennis matches and provides player statistics and mini court visualizations and It utilizes YOLO (You Only Look Once) v8x for player detection and tracking, and fine-tunes YOLOv5 for ball detection and tracking. Additionally, a ResNet50 model is used for keypoint detection and tracking. Usage Clone the repository: 1 git clone https://github.com/Sh-31/Tennis-Analysis-System.git Install the required dependencies: 1 2 pip3 install -r requirements.txt (linux) pip install -r requirements.txt (windows) Run the main script: 1 2 python3 main.py (linux) python main.py (windows) Sample Output Datasets Ball Detection For ball detection, we used the tennis-ball-detection dataset from Roboflow. You can access it at the following link: ...

August 6, 6060 路 2 min 路 281 words 路 Sherif Ahmed