https://github.com/zrkhadija/yoga-pose-recognition-using-cnns

This project employs deep learning techniques to classify yoga poses from images. Using CNNs, the model predicts the pose name for each input image, leveraging techniques like data augmentation and k-fold cross-validation to enhance performance and reliability.
https://github.com/zrkhadija/yoga-pose-recognition-using-cnns

cnn data-augmentation deep-learning evaluation keras tenserflow

Last synced: about 1 month ago
JSON representation

This project employs deep learning techniques to classify yoga poses from images. Using CNNs, the model predicts the pose name for each input image, leveraging techniques like data augmentation and k-fold cross-validation to enhance performance and reliability.

• Host: GitHub
• URL: https://github.com/zrkhadija/yoga-pose-recognition-using-cnns
• Owner: zrkhadija
• Created: 2024-11-23T11:52:49.000Z (about 2 months ago)
• Default Branch: main
• Last Pushed: 2024-11-23T11:56:06.000Z (about 2 months ago)
• Last Synced: 2024-12-07T13:07:54.041Z (about 1 month ago)
• Topics: cnn, data-augmentation, deep-learning, evaluation, keras, tenserflow
• Language: Jupyter Notebook
• Homepage:
• Size: 1.4 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# 🧘‍♀️ Yoga Pose Recognition Using CNNs

This project employs deep learning techniques to classify yoga poses from images. Using CNNs, the model predicts the pose name for each input image, leveraging techniques like data augmentation and k-fold cross-validation to enhance performance and reliability.

# 🚀 Project Highlights

- **🖼️ Yoga Pose Classification** : Predict the yoga pose name from input images.

- **🔄 Data Augmentation**: Use Keras' ImageDataGenerator to improve model robustness by generating variations of the training data.

- **🔍 K-Fold Cross-Validation** : Evaluate the model's performance across multiple data splits for reliable results.

- **🛠️ Keras API with TensorFlow** : Build and train the CNN model using the powerful Keras framework.

  # 📊 Dataset Description

The dataset comprises labeled images of various yoga poses. Each image belongs to a specific category representing a distinct yoga position. Data augmentation was applied to increase the dataset size and variability.

# 🛠️ Technologies Used

- **🐍 Python**: For scripting and data preprocessing.

- **🎛️ TensorFlow/Keras**: For building and training the CNN model.

- **🖼️ ImageDataGenerator**: For data augmentation to generate diverse training samples.

- **📊 scikit-learn**: For implementing k-fold cross-validation.

- **🎨 Matplotlib/Seaborn**: For visualizing results and performance metrics.