NVIDIA Model Deployment – TensorFlow Example

This project demonstrates deploying a simple TensorFlow model using the NVIDIA Deep Learning Institute (DLI) lab environment.

🚀 Project Highlights

• Built and trained a basic TensorFlow model using Keras Sequential API.
• Saved the trained model in SavedModel format under models/simple-tensorflow-model/1.
• Ran inference using dummy input data and verified model predictions.
• Organized and uploaded the model files to GitHub for showcasing.

🗂️ Folder Structure

models/ └── simple-tensorflow-model/ └── 1/ ├── Screenshots/ ├── variables/ │ ├── variables.data-00000-of-00001 │ └── variables.index └── saved_model.pb

📸 Screenshots

• ✅ Model training & saving
• ✅ Folder structure
• ✅ Inference output
• ✅ GitHub hosted model repo

🧠 Skills Practiced

• Model creation with TensorFlow/Keras
• SavedModel format deployment
• Git/GitHub project management
• Hands-on with model inference