muneebnadeem1870/deepfake-detection-swin

🧠 Deepfake Detection using Swin Transformer

A robust deepfake detection model leveraging the microsoft/swin-base-patch4-window7-224 architecture. Built and trained on the "Hemg/deepfake-and-real-images" dataset with oversampling and image augmentations to ensure class balance and improved generalization.

---

📌 Table of Contents

• 📦 Cell1: Install Required Packages
• 📥 Cell2: Load Dataset & Apply Oversampling
• 🏷️ Cell3: Label Mapping + Split Dataset
• 🧠 Cell4: Load Swin Transformer + Transforms
• 📊 Cell5: Collator + Metrics + CSV/Plot Export
• ⚙️ Cell6: Training Arguments + Trainer Setup
• 🚀 Cell7: Train and Evaluate
• 📈 Cell8: Loss & Accuracy Plots

---

📦 Cell1: Install Required Packages

pip install -q datasets transformers evaluate imbalanced-learn
pip install -U transformers

---

📥 Cell2: Load Dataset & Apply Oversampling

Used the Hemg/deepfake-and-real-images dataset and applied RandomOverSampler from imblearn to balance the Real and Fake class distribution.

---

🏷️ Cell3: Label Mapping + Split Dataset

Mapped class labels to integers using ClassLabel and split the dataset using stratification into 60% training and 40% testing.

---

🧠 Cell4: Load Swin Transformer + Transforms

• Loaded Swin Transformer from Hugging Face Transformers.
• Defined different transforms for training and evaluation using torchvision.transforms.

---

📊 Cell5: Collator + Metrics + CSV/Plot Export

• Used a custom collator to batch image tensors and labels.
• Saved evaluation metrics (accuracy, precision, recall, f1) and confusion matrix as .csv and .png.

---

⚙️ Cell6: Training Arguments + Trainer Setup

• Trained using Hugging Face Trainer.
• Setup to run for 2 epochs with the best model saved based on the highest F1 score.

---

🚀 Cell7: Train and Evaluate

Executed training and evaluation using the following:

trainer.train()
trainer.evaluate()

---

📈 Cell8: Loss & Accuracy Plots

Post-training visualizations generated:

---

📂 Files and Artifacts

• classification_report.csv
• confusion_matrix.csv
• confusion_matrix_plot.png
• loss_vs_steps.png
• accuracy_vs_steps.png
• loss_vs_epoch.png
• accuracy_vs_epoch.png
• loss_vs_walltime.png
• accuracy_vs_walltime.png

---

🧩 Model Details

• Backbone: microsoft/swin-base-patch4-window7-224
• Task: Binary Image Classification (Real vs Fake)
• Augmentation: Rotation, Sharpness
• Metrics: Accuracy, Precision, Recall, F1

---

📜 License

MIT License