Update app.py

app.py

@@ -3,6 +3,7 @@ import torch
 from transformers import AutoProcessor, PaliGemmaForConditionalGeneration
 from PIL import Image
 
+# Load model and processor
 model_id = "brucewayne0459/paligemma_derm"
 processor = AutoProcessor.from_pretrained(model_id)
 model = PaliGemmaForConditionalGeneration.from_pretrained(model_id)
@@ -11,7 +12,7 @@ model.eval()
 device = "cuda" if torch.cuda.is_available() else "cpu"
 model.to(device)
 
-# logo (pakai yg huggingface dulu)
+# Logo (Hugging Face)
 st.markdown(
     """
     <style>
@@ -31,9 +32,11 @@ st.markdown(
     unsafe_allow_html=True,
 )
 
+# App Title
 st.title("VisionDerm")
 st.write("Upload an image or use your camera to identify the skin condition.")
 
+# Layout
 col1, col2 = st.columns([3, 2])
 
 with col1:
@@ -48,19 +51,28 @@ input_image = None
 if camera_photo:
     input_image = Image.open(camera_photo)
 elif uploaded_file:
-    input_image = Image.open(uploaded_file)
-
+    try:
+        # Open and convert uploaded file to RGB
+        input_image = Image.open(uploaded_file).convert("RGB")
+        input_image = input_image.copy()  # Detach from file pointer
+    except Exception as e:
+        st.error(f"Error loading image: {str(e)}")
+        input_image = None
+
+# Display and process the image
 with col2:
     if input_image:
-        resized_image = input_image.resize((300, 300))
-        st.image(resized_image, caption="Selected Image (300x300)", use_container_width=True)
+        try:
+            # Display the uploaded or captured image
+            resized_image = input_image.resize((300, 300))
+            st.image(resized_image, caption="Selected Image (300x300)", use_container_width=True)
 
-        # Resize image for processing (512x512 pixels)
-        max_size = (512, 512)
-        processed_image = input_image.resize(max_size)
+            # Resize the image for processing (512x512 pixels)
+            max_size = (512, 512)
+            processed_image = input_image.resize(max_size)
 
-        with st.spinner("Processing..."):
-            try:
+            with st.spinner("Processing..."):
+                # Prepare inputs for the model
                 inputs = processor(
                     text=prompt,
                     images=processed_image,
@@ -68,28 +80,31 @@ with col2:
                     padding="longest"
                 ).to(device)
 
-                default_max_tokens = 50  # Set a default value for max tokens
+                # Generate output from the model
+                default_max_tokens = 50  # Default value for max tokens
                 with torch.no_grad():
                     outputs = model.generate(**inputs, max_new_tokens=default_max_tokens)
 
+                # Decode and clean the output
                 decoded_output = processor.decode(outputs[0], skip_special_tokens=True)
                 if prompt in decoded_output:
                     decoded_output = decoded_output.replace(prompt, "").strip()
-
                 decoded_output = decoded_output.title()
 
+                # Display the result
                 st.success("Analysis Complete!")
                 st.write("**Model Output:**", decoded_output)
 
-            except Exception as e:
-                st.error(f"Error: {str(e)}")
+        except Exception as e:
+            st.error(f"Error: {str(e)}")
 
 st.markdown("---")
+
+# Team Information
 st.info("""
 ### Team: Mahasigma Berprestasi
 - **Muhammad Karov Ardava Barus** ; 103052300001
 - **Akmal Yaasir Fauzaan** ; 103052300008
 - **Farand Diy Dat Mahazalfaa** ; 103052300050
 - **Hauzan Rafi Attallah**; 103052330011
-""")
-
+""")