TensorFlow Notebooks 📓

A curated collection of Jupyter notebooks covering fundamentals and practical applications of TensorFlow for Deep Learning.
This repository is designed as both a learning resource and a reference hub for experimenting with computer vision, natural language processing, transfer learning, and core neural network architectures.

---

📂 Repository Structure

• DLandTF_fundamentals.ipynb
  Basics of Deep Learning and TensorFlow workflow.

• NeuralNetworkClassificationUsingTf.ipynb
  Building classification models using fully connected neural networks.

• NeuralNetworkRegression_with_TF.ipynb
  Regression tasks with TensorFlow — predicting continuous values.

• ComputervisionCNNusingTf.ipynb
  Applying Convolutional Neural Networks (CNNs) for image classification.

• NLP_fundamentals_TF.ipynb
  Natural Language Processing with TensorFlow — text preprocessing and sequence modeling.

• TL_FeatureExtraction__Tf.ipynb
  Transfer learning with feature extraction using pre-trained models.

• Tf_TranferLearning_FineTuning.ipynb
  Fine-tuning pre-trained models for better performance.

• TransferLearning_TF_scaling_up.ipynb
  Scaling up transfer learning techniques for larger datasets and complex tasks.

---

🚀 Features

• Covers core concepts of deep learning with TensorFlow.
• Hands-on implementation of classification, regression, and CNNs.
• Introduces NLP basics with TensorFlow/Keras.
• Practical transfer learning workflows including feature extraction and fine-tuning.
• Each notebook is self-contained with explanations and code.

---

🛠️ Requirements

• Python 3.8+
• TensorFlow 2.x
• Jupyter Notebook / JupyterLab
• NumPy, Pandas, Matplotlib, Scikit-learn

Install dependencies:

pip install tensorflow numpy pandas matplotlib scikit-learn jupyter