|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- prithivMLmods/Deepfake-vs-Real |
|
language: |
|
- en |
|
pipeline_tag: image-classification |
|
library_name: transformers |
|
tags: |
|
- Deepfake |
|
base_model: |
|
- google/vit-base-patch32-224-in21k |
|
--- |
|
 |
|
|
|
# **Deepfake-Detection-Exp-02-22** |
|
|
|
Deepfake-Detection-Exp-02-22 is a minimalist, high-quality dataset trained on a ViT-based model for image classification, distinguishing between deepfake and real images. The model is based on Google's **`google/vit-base-patch32-224-in21k`**. |
|
|
|
```bitex |
|
Mapping of IDs to Labels: {0: 'Deepfake', 1: 'Real'} |
|
|
|
Mapping of Labels to IDs: {'Deepfake': 0, 'Real': 1} |
|
``` |
|
|
|
```python |
|
Classification report: |
|
|
|
precision recall f1-score support |
|
|
|
Deepfake 0.9833 0.9187 0.9499 1600 |
|
Real 0.9238 0.9844 0.9531 1600 |
|
|
|
accuracy 0.9516 3200 |
|
macro avg 0.9535 0.9516 0.9515 3200 |
|
weighted avg 0.9535 0.9516 0.9515 3200 |
|
``` |
|
|
|
|
|
 |
|
|
|
# **Inference with Hugging Face Pipeline** |
|
```python |
|
from transformers import pipeline |
|
|
|
# Load the model |
|
pipe = pipeline('image-classification', model="prithivMLmods/Deepfake-Detection-Exp-02-22", device=0) |
|
|
|
# Predict on an image |
|
result = pipe("path_to_image.jpg") |
|
print(result) |
|
``` |
|
|
|
# **Inference with PyTorch** |
|
```python |
|
from transformers import ViTForImageClassification, ViTImageProcessor |
|
from PIL import Image |
|
import torch |
|
|
|
# Load the model and processor |
|
model = ViTForImageClassification.from_pretrained("prithivMLmods/Deepfake-Detection-Exp-02-22") |
|
processor = ViTImageProcessor.from_pretrained("prithivMLmods/Deepfake-Detection-Exp-02-22") |
|
|
|
# Load and preprocess the image |
|
image = Image.open("path_to_image.jpg").convert("RGB") |
|
inputs = processor(images=image, return_tensors="pt") |
|
|
|
# Perform inference |
|
with torch.no_grad(): |
|
outputs = model(**inputs) |
|
logits = outputs.logits |
|
predicted_class = torch.argmax(logits, dim=1).item() |
|
|
|
# Map class index to label |
|
label = model.config.id2label[predicted_class] |
|
print(f"Predicted Label: {label}") |
|
``` |
|
|
|
# **Limitations** |
|
1. **Generalization Issues** – The model may not perform well on deepfake images generated by unseen or novel deepfake techniques. |
|
2. **Dataset Bias** – The training data might not cover all variations of real and fake images, leading to biased predictions. |
|
3. **Resolution Constraints** – Since the model is based on `vit-base-patch32-224-in21k`, it is optimized for 224x224 image resolution, which may limit its effectiveness on high-resolution images. |
|
4. **Adversarial Vulnerabilities** – The model may be susceptible to adversarial attacks designed to fool vision transformers. |
|
5. **False Positives & False Negatives** – The model may occasionally misclassify real images as deepfake and vice versa, requiring human validation in critical applications. |
|
|
|
# **Intended Use** |
|
1. **Deepfake Detection** – Designed for identifying deepfake images in media, social platforms, and forensic analysis. |
|
2. **Research & Development** – Useful for researchers studying deepfake detection and improving ViT-based classification models. |
|
3. **Content Moderation** – Can be integrated into platforms to detect and flag manipulated images. |
|
4. **Security & Forensics** – Assists in cybersecurity applications where verifying the authenticity of images is crucial. |
|
5. **Educational Purposes** – Can be used in training AI practitioners and students in the field of computer vision and deepfake detection. |
