Update app.py

app.py

@@ -1,143 +1,16 @@
 import gradio as gr
-import torch
-import torch.nn as nn
-from torchvision import transforms
+from transformers import AutoImageProcessor, SiglipForImageClassification
 from PIL import Image
+import torch
 
 # ============================================================
-# MODEL ARCHITECTURE
-# ============================================================
-
-class BasicBlock(nn.Module):
-    expansion = 1
-
-    def __init__(self, in_channels, out_channels, stride=1, downsample=None):
-        super(BasicBlock, self).__init__()
-        
-        self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3,
-                              stride=stride, padding=1, bias=False)
-        self.bn1 = nn.BatchNorm2d(out_channels)
-        
-        self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3,
-                              stride=1, padding=1, bias=False)
-        self.bn2 = nn.BatchNorm2d(out_channels)
-        
-        self.relu = nn.ReLU(inplace=True)
-        self.downsample = downsample
-
-    def forward(self, x):
-        identity = x
-        
-        out = self.conv1(x)
-        out = self.bn1(out)
-        out = self.relu(out)
-        
-        out = self.conv2(out)
-        out = self.bn2(out)
-        
-        if self.downsample is not None:
-            identity = self.downsample(x)
-        
-        out += identity
-        out = self.relu(out)
-        
-        return out
-
-
-class ResNet(nn.Module):
-    def __init__(self, block, layers, num_classes=2):
-        super(ResNet, self).__init__()
-        
-        self.in_channels = 64
-        
-        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
-        self.bn1 = nn.BatchNorm2d(64)
-        self.relu = nn.ReLU(inplace=True)
-        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
-        
-        self.layer1 = self._make_layer(block, 64, layers[0], stride=1)
-        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
-        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
-        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
-        
-        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
-        self.fc = nn.Linear(512 * block.expansion, num_classes)
-
-    def _make_layer(self, block, out_channels, num_blocks, stride):
-        downsample = None
-        
-        if stride != 1 or self.in_channels != out_channels * block.expansion:
-            downsample = nn.Sequential(
-                nn.Conv2d(self.in_channels, out_channels * block.expansion,
-                         kernel_size=1, stride=stride, bias=False),
-                nn.BatchNorm2d(out_channels * block.expansion)
-            )
-        
-        layers = []
-        layers.append(block(self.in_channels, out_channels, stride, downsample))
-        self.in_channels = out_channels * block.expansion
-        
-        for _ in range(1, num_blocks):
-            layers.append(block(self.in_channels, out_channels))
-        
-        return nn.Sequential(*layers)
-
-    def forward(self, x):
-        x = self.conv1(x)
-        x = self.bn1(x)
-        x = self.relu(x)
-        x = self.maxpool(x)
-        
-        x = self.layer1(x)
-        x = self.layer2(x)
-        x = self.layer3(x)
-        x = self.layer4(x)
-        
-        x = self.avgpool(x)
-        x = torch.flatten(x, 1)
-        x = self.fc(x)
-        
-        return x
-
-
-def resnet18(num_classes=2):
-    return ResNet(BasicBlock, [2, 2, 2, 2], num_classes=num_classes)
-
-
-# ============================================================
-# SETUP
+# LOAD MODEL FROM HUGGING FACE HUB
 # ============================================================
 
-device = torch.device('cpu')
-model = None
-
-transform = transforms.Compose([
-    transforms.Resize((256, 256)),
-    transforms.ToTensor(),
-    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
-])
-
-class_names = ['Fake', 'Real']
-
-
-def load_model():
-    global model
-    
-    # Load model directly from uploaded file
-    model_path = 'resnet18_deepfake_best.pth'
-    
-    model = resnet18(num_classes=2)
-    checkpoint = torch.load(model_path, map_location=device)
-    model.load_state_dict(checkpoint['model_state_dict'])
-    model.to(device)
-    model.eval()
-    
-    print("✓ Model loaded!")
-    return model
-
-
-load_model()
-
+model_name = "prithivMLmods/Deepfake-Detect-Siglip2"
+model = SiglipForImageClassification.from_pretrained(model_name)
+processor = AutoImageProcessor.from_pretrained(model_name)
+model.eval()
 
 # ============================================================
 # PREDICTION
@@ -146,29 +19,22 @@ load_model()
 def predict(image):
     if image is None:
         return {"Error": "Upload an image"}
-    
+
     if not isinstance(image, Image.Image):
         image = Image.fromarray(image)
-    
-    image = image.convert('RGB')
-    input_tensor = transform(image).unsqueeze(0).to(device)
-    
+
+    image = image.convert("RGB")
+    inputs = processor(images=image, return_tensors="pt")
+
     with torch.no_grad():
-        outputs = model(input_tensor)
-        probabilities = torch.nn.functional.softmax(outputs, dim=1)
-    
-    # DEBUG: Print raw outputs
-    print(f"Raw outputs: {outputs}")
-    print(f"Probabilities: {probabilities}")
-    print(f"Fake prob: {probabilities[0][0]:.4f}, Real prob: {probabilities[0][1]:.4f}")
-    
-    result = {
-        class_names[0]: float(probabilities[0][0]),
-        class_names[1]: float(probabilities[0][1])
-    }
-    
-    return result
+        outputs = model(**inputs)
+        probs = torch.nn.functional.softmax(outputs.logits, dim=1).squeeze().tolist()
+
+    labels = model.config.id2label
+    result = {labels[i]: round(probs[i], 4) for i in range(len(probs))}
 
+    print(f"Result: {result}")
+    return result
 
 # ============================================================
 # INTERFACE
@@ -183,4 +49,4 @@ demo = gr.Interface(
 )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()