sdfgsdfg

handler.py

@@ -2,11 +2,12 @@ from typing import  Dict, List, Any
 import torch
 import numpy as np
 import torch.nn.functional as F
-
+from serkan import SimpleUpscaleModel
 class EndpointHandler():
-    def __init__(self, path="FiveK.pth"):
+    def __init__(self, path="model_weights.pth"):
         # load the optimized model
-        self.model = torch.load(path)
+        self.model = SimpleUpscaleModel()
+        self.model.load_state_dict(torch.load(self.path))
 
 
 
@@ -25,19 +26,8 @@ class EndpointHandler():
         img = inputs["image"]
 
         # Load the image
-        img = np.float32(img) / 255.  # Load and normalize the image
-
-        # Convert to torch tensor and add batch dimension
-        img_tensor = torch.from_numpy(img).permute(2, 0, 1).unsqueeze(0)
-
-        # Padding if necessary (to make image dimensions multiples of 4)
-        b, c, h, w = img_tensor.shape
-        factor = 4  # Assuming factor is 4, based on the code context
-        H, W = ((h + factor) // factor) * factor, ((w + factor) // factor) * factor
-        padh = H - h if h % factor != 0 else 0
-        padw = W - w if w % factor != 0 else 0
-        img_tensor = F.pad(img_tensor, (0, padw, 0, padh), 'reflect')
+        img = np.float32(img)
 
-        restored = self.model(img_tensor)
+        upscaled = self.model(img)
         # postprocess the prediction
         return "OKAY"

serkan.py

@@ -0,0 +1,38 @@
+import torch
+import torch.nn as nn
+
+class SimpleUpscaleModel(nn.Module):
+    def __init__(self, scale_factor=2):
+        """
+        A simple model for upscaling inputs using bilinear interpolation.
+        
+        Args:
+            scale_factor (int): The factor by which to upscale the input.
+        """
+        super(SimpleUpscaleModel, self).__init__()
+        
+        # Upsampling layer
+        self.upsample = nn.Upsample(scale_factor=scale_factor, mode='bilinear', align_corners=True)
+    
+    def forward(self, x):
+        """
+        Forward pass of the network.
+        
+        Args:
+            x (torch.Tensor): Input tensor of shape (batch_size, channels, height, width).
+        
+        Returns:
+            torch.Tensor: Upscaled output tensor.
+        """
+        return self.upsample(x)
+
+if __name__ == "__main__":
+    # Create the model
+    scale_factor = 2
+    model = SimpleUpscaleModel(scale_factor=scale_factor)
+
+    # Save the model
+    model_path = "model_weights.pth"
+    torch.save(model.state_dict(), model_path)
+
+    print(f"Model saved to {model_path}")