Upload folder using huggingface_hub

Dockerfile

@@ -1,22 +1,14 @@
+# Use a minimal base image with Python
 FROM python:3.9-slim
 
-# Create a non-root user
-RUN adduser --disabled-password --gecos '' streamlit-user
-
+# Set the working directory
 WORKDIR /app
 
+# Copy all files from the local directory to the container
 COPY . .
 
-# Set Streamlit's config directory to the current working directory
-ENV STREAMLIT_SERVER_CONFIG_FILE=/app/.streamlit/config.toml
-
-# Add the user's local bin directory to the PATH
-ENV PATH="/home/streamlit-user/.local/bin:$PATH"
-
-# Install dependencies as the non-root user
-USER streamlit-user
-RUN pip3 install --no-cache-dir -r requirements.txt
-
-EXPOSE 8080
+# Install dependencies
+RUN pip install --no-cache-dir -r requirements.txt
 
-CMD ["streamlit", "run", "app.py", "--server.port=8080", "--server.address=0.0.0.0"]
+# Run the Streamlit app
+CMD ["streamlit", "run", "app.py"]

app.py

@@ -2,12 +2,8 @@ import streamlit as st
 import numpy as np
 from PIL import Image
 from tensorflow.keras.models import load_model
-import os
-import sys
-import platform
-import subprocess
 
-# Add a function to load the model
+# Load the trained VGG16 model
 @st.cache_resource
 def load_vgg_model():
     return load_model("brain_tumor_vgg16_model.keras")
@@ -16,63 +12,28 @@ def load_vgg_model():
 st.title("Brain Tumor MRI Classification App")
 st.write("Upload a brain MRI scan to check if it contains a tumor.")
 
-# --- DEBUGGING INFORMATION ---
-st.header("Debugging Information")
+# Load the model outside the prediction block to prevent reloading on every interaction
+model = load_vgg_model()
 
-# Check current working directory
-st.write(f"Current working directory: {os.getcwd()}")
+uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
 
-# List files in the directory
-st.write("Files in /app:")
-for file in os.listdir("."):
-    st.write(f"- {file}")
+if uploaded_file is not None:
+    # Display the uploaded image
+    image = Image.open(uploaded_file).convert("RGB")
+    st.image(image, caption='Uploaded MRI Scan', use_column_width=True)
 
-# Display Python and library versions
-st.write("Python version:", sys.version)
-st.write("Numpy version:", np.__version__)
-st.write("TensorFlow version:", tf.__version__)
-st.write("Pillow version:", Image.__version__)
-
-# Display environment variables
-st.write("Environment Variables:")
-for key, value in os.environ.items():
-    st.write(f"- {key}: {value}")
-
-# --- END DEBUGGING INFORMATION ---
-
-# Try to load the model and display success/failure
-try:
-    with st.spinner('Loading model...'):
-        model = load_vgg_model()
-    st.success("Model loaded successfully.")
-
-    # Define image size (must match the model's input size)
+    # Preprocess the image for the model
     img_size = 150
-
-    # UI for image upload
-    uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
-
-    if uploaded_file is not None:
-        # Display the uploaded image
-        image = Image.open(uploaded_file).convert("RGB")
-        st.image(image, caption='Uploaded MRI Scan', use_column_width=True)
-        st.write("")
-        st.write("Classifying...")
-
-        # Preprocess the image for the model
-        img_array = np.array(image.resize((img_size, img_size)))
-        img_array = np.expand_dims(img_array, axis=0)
-        img_array = img_array / 255.0
-
-        # Make prediction
-        prediction = model.predict(img_array)
-        class_predicted = (prediction > 0.5).astype("int32")[0][0]
-
-        # Display the result
-        if class_predicted == 1:
-            st.error("Prediction: Tumor Detected")
-        else:
-            st.success("Prediction: No Tumor Detected")
-
-except Exception as e:
-    st.error(f"Failed to load or use the model. Error: {e}")
+    img_array = np.array(image.resize((img_size, img_size)))
+    img_array = np.expand_dims(img_array, axis=0)
+    img_array = img_array / 255.0
+
+    # Make prediction
+    prediction = model.predict(img_array)
+    class_predicted = (prediction > 0.5).astype("int32")[0][0]
+
+    # Display the result
+    if class_predicted == 1:
+        st.error("Prediction: Tumor Detected")
+    else:
+        st.success("Prediction: No Tumor Detected")