deepf 0.1__tar.gz

deepf-0.1/MANIFEST.in

@@ -0,0 +1 @@
+include deepf/data.txt

deepf-0.1/PKG-INFO

@@ -0,0 +1,3 @@
+Metadata-Version: 2.4
+Name: deepf
+Version: 0.1

deepf-0.1/deepf/__init__.py

@@ -0,0 +1,2 @@
+from importlib.resources import files
+print(files("deepf").joinpath("data.txt").read_text())

deepf-0.1/deepf/data.txt

@@ -0,0 +1,78 @@
+import torch
+import torch.nn as nn
+import torchvision as tv
+from torch.utils.data import DataLoader
+from torch import optim
+from PIL import Image
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Image transform
+transform = tv.transforms.Compose([
+    tv.transforms.Resize((224,224)),
+    tv.transforms.ToTensor()
+])
+
+# Load dataset (folder must contain 'fake' and 'real')
+dataset = tv.datasets.ImageFolder("/content/drive/MyDrive/MSCIT/SEM2/CF/content/train", transform=transform)
+loader = DataLoader(dataset, batch_size=8, shuffle=True)
+
+# Simple CNN model
+class DeepFakeNet(nn.Module):
+    def __init__(self):
+        super().__init__()
+        self.conv = nn.Sequential(
+            nn.Conv2d(3,8,3,padding=1), nn.ReLU(), nn.MaxPool2d(2),
+            nn.Conv2d(8,16,3,padding=1), nn.ReLU(), nn.MaxPool2d(2)
+        )
+        self.fc = nn.Sequential(
+            nn.Flatten(),
+            nn.Linear(16*56*56,2)
+        )
+
+    def forward(self,x):
+        x = self.conv(x)
+        x = self.fc(x)
+        return x
+
+model = DeepFakeNet().to(device)
+
+# Loss and optimizer
+loss_fn = nn.CrossEntropyLoss()
+optimizer = optim.Adam(model.parameters(), lr=0.001)
+
+# Training loop
+for images, labels in loader:
+    images, labels = images.to(device), labels.to(device)
+
+    optimizer.zero_grad()
+    outputs = model(images)
+    loss = loss_fn(outputs, labels)
+    loss.backward()
+    optimizer.step()
+
+print("Training Done!")
+
+# Save model
+torch.save(model.state_dict(), "deepfake_model.pth")
+
+import torch
+from PIL import Image
+import torchvision.transforms as T
+
+model = DeepFakeNet()
+model.load_state_dict(torch.load("deepfake_model.pth"))
+model.eval()
+
+transform = T.Compose([
+    T.Resize((224,224)),
+    T.ToTensor()
+])
+
+img = Image.open("/content/drive/MyDrive/MSCIT/SEM2/CF/content/train/real/real1.jpg").convert("RGB")
+img = transform(img).unsqueeze(0)
+
+output = model(img)
+pred = torch.argmax(output)
+
+print("Prediction:", "Fake" if pred==0 else "Real")

deepf-0.1/deepf.egg-info/PKG-INFO

@@ -0,0 +1,3 @@
+Metadata-Version: 2.4
+Name: deepf
+Version: 0.1

deepf-0.1/deepf.egg-info/SOURCES.txt

@@ -0,0 +1,9 @@
+MANIFEST.in
+pyproject.toml
+setup.py
+deepf/__init__.py
+deepf/data.txt
+deepf.egg-info/PKG-INFO
+deepf.egg-info/SOURCES.txt
+deepf.egg-info/dependency_links.txt
+deepf.egg-info/top_level.txt

deepf-0.1/deepf.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

deepf-0.1/deepf.egg-info/top_level.txt

@@ -0,0 +1 @@
+deepf

deepf-0.1/pyproject.toml

@@ -0,0 +1,3 @@
+[build-system]
+requires = ["setuptools", "wheel"]
+build-backend = "setuptools.build_meta"

deepf-0.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

deepf-0.1/setup.py

@@ -0,0 +1,9 @@
+from setuptools import setup, find_packages
+
+setup(
+    name="deepf",
+    version="0.1",
+    packages=find_packages(),
+    include_package_data=True,
+    package_data={"deepf": ["data.txt"]},
+)