Update app.py

app.py

@@ -9,10 +9,12 @@ import shinyswatch
 from shiny import App, Inputs, Outputs, Session, reactive, render, req, ui
 
 import os
-# os.environ["TRANSFORMERS_CACHE"] = "./hf_cache"
 from transformers import SamModel, SamConfig, SamProcessor
 import torch
 
+from PIL import Image
+import io
+
 sns.set_theme()
 
 dir = Path(__file__).resolve().parent
@@ -59,22 +61,16 @@ app_ui = ui.page_fillable(
     ),
 )
 
+def tif_bytes_to_pil_image(tif_bytes):
+  # Create a BytesIO object from the TIFF bytes
+  bytes_io = io.BytesIO(tif_bytes)
+
+  # Open the BytesIO object as an Image
+  image = Image.open(bytes_io)
+
+  return image
 
 def server(input: Inputs, output: Outputs, session: Session):
-    # Load the model configuration
-    model_config = SamConfig.from_pretrained("facebook/sam-vit-base")
-    processor = SamProcessor.from_pretrained("facebook/sam-vit-base")
-    
-    # Create an instance of the model architecture with the loaded configuration
-    model = SamModel(config=model_config)
-    # Update the model by loading the weights from saved file
-    model_state_dict = torch.load(str(dir / "checkpoint.pth"), map_location=torch.device('cpu'))
-    model.load_state_dict(model_state_dict)
-    
-    # set the device to cuda if available, otherwise use cpu
-    device = "cuda" if torch.cuda.is_available() else "cpu"
-    model.to(device)
-    
     @reactive.Calc
     def uploaded_image_path() -> str:
         """Returns the path to the uploaded image"""
@@ -92,6 +88,58 @@ def server(input: Inputs, output: Outputs, session: Session):
             return img
         else:
             return None  # Return an empty string if no image is uploaded
+            
+    def process_image():
+        """Processes the uploaded image, loads the model, and evaluates to get predictions"""
+        # Load the uploaded image
+        uploaded_image_bytes = input.tile_image()[0].read()
+
+        # Convert the uploaded TIFF bytes to a PIL Image object
+        uploaded_image = tif_bytes_to_pil_image(uploaded_image_bytes)
+
+        # Perform any preprocessing steps on the image as needed
+        
+        # Example: Convert the image to the required input format for the model
+        # image_array = preprocess_image(uploaded_image)
+
+        # Load the model configuration
+        model_config = SamConfig.from_pretrained("facebook/sam-vit-base")
+        processor = SamProcessor.from_pretrained("facebook/sam-vit-base")
+        
+        # Create an instance of the model architecture with the loaded configuration
+        model = SamModel(config=model_config)
+        # Update the model by loading the weights from saved file
+        model_state_dict = torch.load(str(dir / "checkpoint.pth"), map_location=torch.device('cpu'))
+        model.load_state_dict(model_state_dict)
+        
+        # set the device to cuda if available, otherwise use cpu
+        device = "cuda" if torch.cuda.is_available() else "cpu"
+        model.to(device)
+        
+        # Evaluate the image with the model
+        # Example: predictions = model.predict(image_array)
+        
+        # Return the processed result (replace 'result' with the actual processed result)
+        return "Processed result"
+
+    @reactive.Calc
+    def processed_result():
+        """Processes the image when uploaded"""
+        if input.tile_image() is not None:
+            return process_image()
+        else:
+            return None
+
+    @output
+    @render.text
+    def processed_output():
+        """Displays the predictions of the uploaded image"""
+        return processed_result()
+    
+
+
+
+    
     
     @reactive.Calc
     def filtered_df() -> pd.DataFrame: