Update handler.py

handler.py

@@ -1,6 +1,3 @@
-# handler.py
-# Save only the weights
-
 import torch
 import torch.nn as nn
 from torchvision import transforms
@@ -9,24 +6,95 @@ from huggingface_hub import hf_hub_download
 import io
 import base64
 
-model = UNet()
+# --- Basic UNet Components ---
+class DoubleConv(nn.Module):
+    def __init__(self, in_channels, out_channels):
+        super().__init__()
+        self.double_conv = nn.Sequential(
+            nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1),
+            nn.ReLU(inplace=True),
+            nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1),
+            nn.ReLU(inplace=True)
+        )
+
+    def forward(self, x):
+        return self.double_conv(x)
+
+class Down(nn.Module):
+    def __init__(self, in_channels, out_channels):
+        super().__init__()
+        self.maxpool_conv = nn.Sequential(
+            nn.MaxPool2d(2),
+            DoubleConv(in_channels, out_channels)
+        )
+
+    def forward(self, x):
+        return self.maxpool_conv(x)
+
+class Up(nn.Module):
+    def __init__(self, in_channels, out_channels, bilinear=True):
+        super().__init__()
+        if bilinear:
+            self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
+        else:
+            self.up = nn.ConvTranspose2d(in_channels // 2, in_channels // 2, kernel_size=2, stride=2)
+        self.conv = DoubleConv(in_channels, out_channels)
+
+    def forward(self, x1, x2):
+        x1 = self.up(x1)
+        diffY = x2.size()[2] - x1.size()[2]
+        diffX = x2.size()[3] - x1.size()[3]
+        x1 = nn.functional.pad(x1, [diffX // 2, diffX - diffX // 2,
+                                    diffY // 2, diffY - diffY // 2])
+        x = torch.cat([x2, x1], dim=1)
+        return self.conv(x)
+
+class OutConv(nn.Module):
+    def __init__(self, in_channels, out_channels):
+        super(OutConv, self).__init__()
+        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=1)
 
-torch.save(model.state_dict(), "UNet_Model.pth")
+    def forward(self, x):
+        return self.conv(x)
 
-# Define your UNet class here (shortened version for example)
+# --- UNet Architecture ---
 class UNet(nn.Module):
-    def __init__(self):  # Add your actual init params
-        super(UNet, self).__init__()
-        # Define layers...
+    def __init__(self, n_channels=3, n_classes=1, bilinear=True):
+        super().__init__()
+        self.n_channels = n_channels
+        self.n_classes = n_classes
+        self.bilinear = bilinear
+
+        self.inc = DoubleConv(n_channels, 64)
+        self.down1 = Down(64, 128)
+        self.down2 = Down(128, 256)
+        self.down3 = Down(256, 512)
+        factor = 2 if bilinear else 1
+        self.down4 = Down(512, 1024 // factor)
+        self.up1 = Up(1024, 512 // factor, bilinear)
+        self.up2 = Up(512, 256 // factor, bilinear)
+        self.up3 = Up(256, 128 // factor, bilinear)
+        self.up4 = Up(128, 64, bilinear)
+        self.outc = OutConv(64, n_classes)
 
     def forward(self, x):
-        # Implement forward pass
-        return x
+        x1 = self.inc(x)
+        x2 = self.down1(x1)
+        x3 = self.down2(x2)
+        x4 = self.down3(x3)
+        x5 = self.down4(x4)
+        x = self.up1(x5, x4)
+        x = self.up2(x, x3)
+        x = self.up3(x, x2)
+        x = self.up4(x, x1)
+        logits = self.outc(x)
+        return torch.sigmoid(logits)
 
+# --- Endpoint Handler ---
 class EndpointHandler:
     def __init__(self, path=""):
         model_path = hf_hub_download(repo_id="whitney0507/unet-model", filename="UNet_Model.pth")
-        self.model = UNet()  # Instantiate model
+        self.model = UNet()
         self.model.load_state_dict(torch.load(model_path, map_location="cpu"))
         self.model.eval()
         self.transform = transforms.Compose([
@@ -41,11 +109,9 @@ class EndpointHandler:
 
         with torch.no_grad():
             output = self.model(input_tensor)
-            pred = output.argmax(dim=1).squeeze().byte().cpu().numpy()
+            mask = (output > 0.5).int().squeeze().byte().cpu().numpy()
 
-        # Convert to base64
-        output_img = Image.fromarray(pred * 255)
+        result_img = Image.fromarray(mask * 255)
         buffer = io.BytesIO()
-        output_img.save(buffer, format="PNG")
+        result_img.save(buffer, format="PNG")
         return {"prediction": base64.b64encode(buffer.getvalue()).decode("utf-8")}
-