Loading repository data…
De-Subhadip / repository
A collection of Jupyter notebooks for various computer vision tasks using Keras, KerasCV, and TensorFlow. Includes image classification, object detection, and advanced deep learning techniques. Covers data preprocessing, augmentation, model training, and evaluation.
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
Welcome to the Computer-Vision-Notebooks repository! This collection of Jupyter notebooks demonstrates practical applications of deep learning in computer vision. Whether you're exploring image classification, object detection, or data augmentation, this repository is built for both beginners and advanced practitioners in the field of AI and computer vision.
Using popular frameworks such as TensorFlow, Keras, and KerasCV, these notebooks offer an end-to-end workflow — from data preprocessing to model evaluation — designed to make learning and implementing computer vision tasks easy and effective.
Some features of the notebooks in this repo are as follows:
End-to-End Workflows:
Each notebook walks you through the complete workflow for solving computer vision tasks, from organizing data to training and evaluating models.
Pre-trained Model Integration:
Easily fine-tune pre-trained models from TensorFlow, Keras, and KerasCV for custom tasks without starting from scratch.
Advanced Data Augmentation Techniques:
Provides comprehensive examples of data augmentation strategies to increase model generalization, making models more robust.
Selected from shared topics, language and repository description—not editorial ratings.
tachodril /
A Collection of Jupyter Notebooks with Deep Learning Models created using Pytorch for Computer Vision (Image Classification) problems trained on GPU.
33/100 healthramesh-dev-code /
This repository is a collection of Python scripts and Jupyter notebooks for understanding the performance improvement in image classification, object detection and instance segmentation with OpenVINO. It also contains reference implementations of dwell time analytics, ALPR and polyp detection.
67/100 healthReal-time Performance Monitoring:
See how your model performs with real-time metrics and interactive plots that help you better understand model learning.
Scalable for Industry Use:
Suitable for adapting the notebooks for real-world use cases in industries like healthcare, retail, or autonomous vehicles.
Well-Structured Notebooks:
Clean, easy-to-follow notebooks designed for readability and effective learning. Each notebook is divided into clear sections to make complex workflows understandable.
Each notebook in this repository follows a well-defined workflow:
📁 Data Organization:
Datasets are properly segregated into folders and subfolders according to target classes.
🔄 Data Preprocessing:
Handling missing values, resizing images, and normalizing the data for better model performance.
🎨 Data Augmentation:
Techniques like rotation, flipping, zooming, and color shifts to artificially expand the dataset and improve generalization.
🧠 Model Building / Importing Pre-trained Models:
Building or fine-tuning models using state-of-the-art architectures like ResNet, EfficientNet, or custom models.
🏋️ Model Training:
Training deep learning models with feedback on accuracy and loss during each epoch.
📊 Model Evaluation:
Generating precision, recall, F1 score, confusion matrices, and other metrics to assess the model's performance.
To get started with the notebooks, follow these steps:
Clone this repository:
git clone https://github.com/De-Subhadip/Computer-Vision-notebooks.git
Navigate to the project folder:
cd Computer-Vision-notebooks
Run Jupyter Notebooks: Launch Jupyter Notebook to explore and execute the notebooks:
jupyter notebook
Start experimenting: Choose the notebook you'd like to explore, and follow the instructions for training models, data preprocessing, and evaluating results.
| Task | Description | Frameworks |
|---|---|---|
| Image Classification | Fine-tuned models for classifying images into various categories | Keras, KerasCV, Tensorflow |
| Object Detection | Detecting objects in images with pre-trained models and transfer learning | Keras, KerasCV |
| Data Augmentation | Techniques like rotation, flipping, and scaling to enhance training data, and some advanced techniques such as CutMix and MixUp | Keras, KerasCV, Tensorflow |
| Model Evaluation | Detailed performance evaluation including precision, recall, and confusion matrices | Keras, KerasCV, Tensorflow |
yashashwita20 /
A collection of my Jupyter notebooks, showcasing my exploration and learning journey in the field of Computer Vision
31/100 healthEmarhnuel /
A collection of computer vision projects using Keras and TensorFlow. Learn about CNNs, regularization, and using pre-trained models for image classification in these Jupyter Notebooks.
27/100 healthareebashakeel101 /
A comprehensive collection of Deep Learning models implemented in Jupyter Notebooks, covering various computer vision and natural language processing tasks including image classification, object detection, image captioning, and generative models.
42/100 health