Update app.py

app.py

@@ -4,8 +4,7 @@ import numpy as np
 import pandas as pd
 import requests
 from io import BytesIO
-from fastai.vision.all import load_learner, untar_data, URLs
-import gradio as gr
+from fastai.vision.all import load_learner  # Corrected import
 
 # Initialize Streamlit app
 st.title("White Blood Cell Classifier")
@@ -13,55 +12,40 @@ st.title("White Blood Cell Classifier")
 # Load the FastAI model for WBC identification
 fastai_model = load_learner('model1.pkl')
 
-# Pre-load some example images with their corresponding labels
-example_images = {
-    "Eosinophil": "eosinophil.jpg",
-    "Lymphocyte": "lymphocyte.jpg",
-    "Monocyte": "monocyte.jpg",
-    "Neutrophil": "neutrophil.jpg",
-}
-
-# Provide a choice of example images
-st.sidebar.header("Example Images")
-example_choice = st.sidebar.selectbox(
-    "Select an example image to classify",
-    list(example_images.keys())
-)
-
-# Display the chosen example image
-example_url = example_images[example_choice]
-response = requests.get(example_url)
-example_image = Image.open(BytesIO(response.content))
-st.sidebar.image(example_image, caption=f"Example: {example_choice}", use_column_width=True)
-
 # File uploader for image input
-uploaded_file = st.file_uploader("Upload your own image for classification", type=["jpg", "png"])
+uploaded_file = st.file_uploader("Upload an image for classification", type=["jpg", "png"])
 
-# Check if an image has been uploaded or an example has been selected
-image_to_classify = example_image if uploaded_file is None else Image.open(uploaded_file)
+if uploaded_file:
+    # Open the uploaded image
+    image = Image.open(uploaded_file)
+    
+    # Display the uploaded image with a caption
+    st.image(image, caption="Uploaded Image", use_column_width=True)
 
-# Display the image being classified
-st.image(image_to_classify, caption="Image for Classification", use_column_width=True)
+    # Perform inference with the FastAI model
+    pred, idx, probs = fastai_model.predict(image)
 
-# Perform inference with the FastAI model
-pred, idx, probs = fastai_model.predict(image_to_classify)
+    # Display a title for the results section
+    st.subheader("White Blood Cell Classification Results")
 
-# Display a subheader for results
-st.subheader("White Blood Cell Classification Results")
+    # Define categories for classification
+    categories = ('EOSINOPHIL', 'LYMPHOCYTE', 'MONOCYTE', 'NEUTROPHIL')
 
-# Define categories for classification
-categories = ('EOSINOPHIL', 'LYMPHOCYTE', 'MONOCYTE', 'NEUTROPHIL')
+    # Create a DataFrame with classification probabilities
+    results_df = pd.DataFrame(
+        {'Cell Type': categories, 'Probability': probs.tolist()}
+    )
 
-# Create a DataFrame with classification probabilities
-results_df = pd.DataFrame({'Cell Type': categories, 'Probability': probs.tolist()})
+    # Display the probabilities as a bar chart
+    st.bar_chart(results_df.set_index('Cell Type'))
 
-# Display probabilities as a bar chart
-st.bar_chart(results_df.set_index('Cell Type'))
+    # Highlight the most likely class
+    most_likely_class = categories[idx]
+    st.success(f"Predicted Class: {most_likely_class}")
 
-# Highlight the most likely class
-most_likely_class = categories[idx]
-st.success(f"Predicted Class: {most_likely_class}")
+    # Additional information about the probabilities
+    st.write("Detailed Classification Results:")
+    st.table(results_df)
 
-# Additional information about probabilities
-st.write("Detailed Classification Results:")
-st.table(results_df)
+else:
+    st.warning("Upload an image to start classification.")