Upload 7 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+best_model_.keras filter=lfs diff=lfs merge=lfs -text

ann_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f66f3a528dfb14e5e37f1c69ca59533cf1c3db4b091693108af5e31f1029b2d1
+size 154741566

app.py

@@ -0,0 +1,94 @@
+import streamlit as st
+import tensorflow as tf
+import pickle
+from tensorflow.keras.preprocessing import image
+import numpy as np
+
+# Function to preprocess the image
+def preprocess_image(img_path, img_height, img_width, model_type="CNN"):
+    # Load the image and convert to grayscale
+    img = image.load_img(img_path, target_size=(img_height, img_width), color_mode='grayscale')
+    img_array = image.img_to_array(img)
+
+    # Normalize the image array
+    img_array = img_array / 255.0  # Normalize for all models
+
+    if model_type in ["Logistic Regression", "Decision Tree"]:
+        img_array = img_array.flatten()  # Flatten for Logistic Regression and Decision Tree
+        img_array = np.expand_dims(img_array, axis=0)  # Add batch dimension
+    else:
+        img_array = np.expand_dims(img_array, axis=0)  # Add batch dimension for CNN and ANN
+
+    return img_array
+
+# Load the Keras model
+@st.cache_resource
+def load_keras_model():
+    return tf.keras.models.load_model('best_model_.keras')
+
+# Load the other models
+@st.cache_resource
+def load_pickle_model(model_path):
+    with open(model_path, 'rb') as f:
+        return pickle.load(f)
+
+# Define model paths and validation accuracies
+models_info = {
+    "ANN Model": {
+        "path": "ann_model.pkl",
+        "accuracy": 0.60
+    },
+    "Decision Tree": {
+        "path": "decision_tree_classifier_model.pkl",
+        "accuracy": 0.70
+    },
+    "Logistic Regression": {
+        "path": "logistic_regression_model.pkl",
+        "accuracy": 0.60
+    },
+    "CNN Model": {
+        "path": "best_model_.keras",
+        "accuracy": 0.90
+    }
+}
+
+# Streamlit UI
+st.title("X-ray Image Classification")
+st.write("Upload an X-ray image to classify it as Normal or Pneumonia.")
+
+# Model selection
+model_name = st.selectbox("Choose a model:", list(models_info.keys()))
+
+# Display selected model accuracy
+st.write(f"Selected Model: {model_name}")
+st.write(f"Validation Accuracy: {models_info[model_name]['accuracy'] * 100:.2f}%")
+
+# Load the selected model
+if model_name == "CNN Model":
+    model = load_keras_model()
+else:
+    model = load_pickle_model(models_info[model_name]["path"])
+
+# File uploader for image
+uploaded_file = st.file_uploader("Choose an X-ray image...", type="jpeg")
+
+if uploaded_file is not None:
+    with open("temp.jpeg", "wb") as f:
+        f.write(uploaded_file.getbuffer())
+    
+    # Use the appropriate preprocessing for the selected model
+    img_height, img_width = 224, 224  # Use the same dimensions as used during training
+    preprocessed_img = preprocess_image(
+        "temp.jpeg", 
+        img_height, 
+        img_width,
+        model_type=model_name  # Pass the model name directly
+    )
+    
+    st.image(uploaded_file, caption="Uploaded X-ray Image", use_column_width=True)
+    
+    # Prediction logic
+    prediction = model.predict(preprocessed_img)
+    prediction_label = "Pneumonia" if prediction[0] > 0.5 else "Normal"
+
+    st.write(f"Prediction: {prediction_label} (Model: {model_name})")

best_model_.keras

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10fa4e3be07ff95be1cfd8b14a1a332d6798e2cad3175b524b286650818e5533
+size 532793354

decision_tree_classifier_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba187cb3ae4b84508751e6e975a1cffc7900e399c8bbbc3312a6d8ab94830c47
+size 47851

dockerfile

@@ -0,0 +1,20 @@
+# Use an official Python runtime as a parent image
+FROM python:3.9-slim
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Copy the requirements file into the container
+COPY requirements.txt ./
+
+# Install any necessary dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the rest of the application code into the container
+COPY . .
+
+# Expose the port the app runs on
+EXPOSE 8501
+
+# Command to run the Streamlit app
+CMD ["streamlit", "run", "app.py"]

logistic_regression_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27fc617fd13a31c2aa9ff3f248df5e7f09dd1bb8485c0d783d31503093b90769
+size 1606853

requirements.txt

@@ -0,0 +1,10 @@
+tensorflow 
+opencv-python 
+matplotlib
+streamlit
+numpy
+scipy
+scikit-learn
+keras_tuner
+scikeras
+lime