{"id":29022017,"url":"https://github.com/anis196/bitesense","last_synced_at":"2025-06-26T02:33:04.612Z","repository":{"id":278345108,"uuid":"931677194","full_name":"Anis196/BiteSense","owner":"Anis196","description":"This project is a deep learning-based classification model using ResNet50 and TensorFlow to classify snake bites as Poisonous or Non-Poisonous based on wound patterns. The model is trained on an image dataset and fine-tuned for better accuracy using GPU.","archived":false,"fork":false,"pushed_at":"2025-06-23T15:14:54.000Z","size":27,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-23T16:33:20.249Z","etag":null,"topics":["cuda-toolkit","cudnn","deep-neural-networks","python","resnet-50","tensorflow-gpu"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Anis196.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-02-12T17:13:56.000Z","updated_at":"2025-06-23T15:14:57.000Z","dependencies_parsed_at":null,"dependency_job_id":"677fc82e-1f20-497b-b2a2-24952a9e684d","html_url":"https://github.com/Anis196/BiteSense","commit_stats":null,"previous_names":["anis196/snk-bite-det","anis196/bitesense"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Anis196/BiteSense","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Anis196%2FBiteSense","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Anis196%2FBiteSense/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Anis196%2FBiteSense/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Anis196%2FBiteSense/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Anis196","download_url":"https://codeload.github.com/Anis196/BiteSense/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Anis196%2FBiteSense/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261986542,"owners_count":23240659,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cuda-toolkit","cudnn","deep-neural-networks","python","resnet-50","tensorflow-gpu"],"created_at":"2025-06-26T02:30:58.556Z","updated_at":"2025-06-26T02:33:04.600Z","avatar_url":"https://github.com/Anis196.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🐍BiteSense : Snake Bite Classification using GPU acceleration\n\nThis project is a **deep learning-based classification model** using **ResNet50** and **TensorFlow** to classify **snake bites as Poisonous or Non-Poisonous** based on wound patterns. The model is trained on an image dataset and fine-tuned for better accuracy using GPU.  \n\n---\n\n## 🚀 Features  \n✅ **Deep Learning Model**: Uses ResNet50 as a feature extractor.  \n✅ **Transfer Learning**: Fine-tuned for improved accuracy.  \n✅ **Data Augmentation**: Helps generalization on unseen data.  \n✅ **Real-time Predictions**: Classifies images of snake bites.  \n✅ **GPU Acceleration**: Supports CUDA for faster training.  \n\n---\n\n## 🛠️ Installation \u0026 Setup  \n\n### 1️⃣ Clone the Repository  \n```bash\ngit clone https://github.com/anis196/snk-bite-det.git\ncd snk-bite-det\n```\n\n### 2️⃣ Install Dependencies  \n```bash\npip install -r requirements.txt\n```\n\n### 3️⃣ Check GPU Availability (Optional)  \n```python\nimport tensorflow as tf\nprint(\"Num GPUs Available:\", len(tf.config.list_physical_devices('GPU')))\n```\n\n### 4️⃣ Prepare the Dataset  \nOrganize the dataset in the following structure:  \n```plaintext\n/dataset  \n    /Poisonous  \n        - image1.jpg  \n        - image2.jpg  \n    /Non_Poisonous  \n        - image1.jpg  \n        - image2.jpg  \n```\n🔹 **Update the dataset path** in `snk.py` before running the script.\n\n---\n\n## 🎯 Model Training \u0026 Usage  \n\n### 5️⃣ Train or Load the Model  \nIf running for the first time, the model will train and save automatically.  \n```bash\npython snk.py\n```\nTo avoid retraining, the model is saved as `resnet50_snake_bite_classifier.h5` and will be loaded in future runs.\n\n---\n\n## 🐍 Making Predictions  \nUse an image file to test the model:  \n```python\nfrom snk import predict_image\n\npredict_image(\"path_to_new_image.jpg\", model)\n```\n### **🔹 Example Output:**  \n```plaintext\nPredicted: Poisonous 🐍 (Confidence: 0.87)\n```\nor  \n```plaintext\nPredicted: Non-Poisonous ✅ (Confidence: 0.93)\n```\n\n---\n\n## 🛠️ Tools \u0026 Technologies Used  \n🔹 **Programming:** Python  \n🔹 **Frameworks:** TensorFlow, Keras  \n🔹 **Libraries:** OpenCV, NumPy, Matplotlib  \n🔹 **Database \u0026 Storage:** Local Storage  \n🔹 **Version Control:** Git  \n\n---\n## 📍THE TRAINED MODEL HASN'T BEEN ADDED DUE TO ITS EXCESSIVE FILE SIZE\n\n## 📜 License  \nThis project is licensed under the [**MIT License**](https://github.com/Anis196/Snk-bite-det/blob/main/LICENSE).  \n\n---\n\n## 📬 Contact  \nFor any queries, reach out at ✉️ [shaikhanis2004@gmail.com](mailto:shaikhanis2004@gmail.com).  \n\n---\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanis196%2Fbitesense","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fanis196%2Fbitesense","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanis196%2Fbitesense/lists"}