Deepfake Detection Efficientnet Vit

deepfake-efficientvit/
│
├── model.py                  # ImprovedEfficientViT class
├── inference.py              # Functions to run inference on videos
├── model.pth  # Trained weights
├── config.json               # Optional model metadata
├── requirements.txt          # Required packages
├── README.md

from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
import torch
from model import ImprovedEfficientViT
from inference import predict_vedio 

# 1️⃣ Download the checkpoint from Hugging Face
checkpoint_path = hf_hub_download(
    repo_id="faisalishfaq2005/deepfake-detection-efficientnet-vit",  
    filename="model.safetensors"
)

# 2️⃣ Load the model weights safely
state_dict = load_file(checkpoint_path, device="cpu")
model = ImprovedEfficientViT()
model.load_state_dict(state_dict)
model.eval()

# 4️⃣ Move to GPU if available
device = "cuda" if torch.cuda.is_available() else "cpu"
model.to(device)

# 3️⃣ Run inference on a video
video_path = "sample_video.mp4"
result = predict_vedio(video_path, model)
print(result)
# Example Output: {'class': 1}