Add falcondemo.mp4 and .keras model to Git LFS

.env.example

@@ -0,0 +1,5 @@
+AI71_API_KEY= # Get at https://marketplace.ai71.ai/api-keys
+ROBOFLOW_API_KEY= # Get at https://app.roboflow.com/
+
+INFERENCE_API_URL=
+INFERENCE_API_KEY=

.gitattributes

@@ -33,5 +33,7 @@ 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
+frontend/react-code/src/assets/falcondemo.mp4 filter=lfs diff=lfs merge=lfs -text
+frontend/FINAL_MODEL.keras filter=lfs diff=lfs merge=lfs -text
 *.jpeg filter=lfs diff=lfs merge=lfs -text
 *.jpg filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,14 @@
+*.pyc
+__pycache__/
+db.sqlite3
+.env
+.conda/
+.venv/
+.vscode/
+
+backend/.hc_backend
+backend/api/migrations/*
+
+frontend/.hc_frontend
+.aider*
+frontend/.streamlit/secrets.toml

.streamlit/secrets.toml

@@ -0,0 +1,3 @@
+INFERENCE_API_URL = "https://detect.roboflow.com"
+INFERENCE_API_KEY = "LSbJ0tl3WTLn4Aqar0Sp"
+AI71_API_KEY = "api71-api-1a7b704d-f950-4507-95cc-c26ce3457d75"

Disease_Detection/app.py

@@ -0,0 +1,80 @@
+import streamlit as st
+from PIL import Image
+import tensorflow as tf
+import cv2
+import numpy as np
+
+# Load the model
+try:
+    model = tf.keras.models.load_model('FINAL_MODEL.keras')
+except FileNotFoundError:
+    st.error("Disease classification model not found. Please ensure 'FINAL_MODEL.keras' is in the same directory as this app.")
+    model = None
+
+# Title of the app
+st.title("DISEASE DETECTION n CLASSIFICATION")
+
+# Upload an image file
+uploaded_image = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
+
+if uploaded_image is not None and model is not None:
+
+    img_opened = Image.open(uploaded_image).convert('RGB')
+    #image_opened = Image.open(uploaded_image)
+    image_pred = np.array(img_opened)
+    image_pred = cv2.resize(image_pred, (150, 150))
+
+    # Convert the image to a numpy array
+    image_pred = np.array(image_pred)
+
+    # Rescale the image (if the model was trained with rescaling)
+    image_pred = image_pred / 255.0
+
+    # Add an extra dimension to match the input shape (1, 150, 150, 3)
+    image_pred = np.expand_dims(image_pred, axis=0)
+
+    # Print the shape of the preprocessed image
+    print("Shape of the preprocessed image:", image_pred.shape)
+
+    # Predict using the model
+    prediction = model.predict(image_pred)
+    
+    # Example prediction output
+    prediction = np.array(prediction)
+
+    #print(f"Prediction_Classes for different types\ncovid: 0\nnormal_chestray: 1\npneumonia: 2")
+    
+    # Get the predicted class
+    predicted_ = np.argmax(prediction)
+    # Display the image
+    print(f"Predicted array for : {predicted_}")
+
+    # Decode the prediction
+    if predicted_ == 0:
+        predicted_class= "Covid"
+    elif predicted_ == 1:
+        predicted_class= "Normal_chestray"
+    else:
+        predicted_class= "Pneumonia"
+
+    # Print the predicted class
+    print(f'The predicted class is: {predicted_class}')
+    #print(prediction)
+
+
+    st.image(image_pred, caption='Input image by user', use_column_width=True)
+    st.write("CLasses description for understanding")
+    st.write("Prediction Classes for different types:")
+    st.write("COVID: 0")
+    st.write("Normal Chest X-ray: 1")
+    st.write("Pneumonia: 2")
+    st.write("\n")
+    # Display some text
+    st.write("DETECTED DISEASE DISPLAY")
+    st.write(f"Predicted Class : {predicted_}")
+    st.write(predicted_class)
+else:
+    st.write("Please upload an image file or ensure the disease model is loaded.")
+
+
+

Disease_Detection/code

@@ -0,0 +1 @@
+

Disease_Detection/requirements.txt

@@ -0,0 +1,7 @@
+opencv-python
+opencv-python-headless
+opencv-contrib-python
+pillow
+tensorflow
+scikit-learn
+streamlit