add codebase for web app

webapp/params.py

@@ -0,0 +1,4 @@
+SECRET_KEY = 'XNet@123'
+UPLOAD_FOLDER = 'webapp/uploads'
+ALLOWED_EXTENSIONS = {'png', 'jpg', 'jpeg'}
+MAX_CONTENT_LENGTH = 8 * 1000 * 1000

webapp/views.py

@@ -0,0 +1,57 @@
+import os
+from webapp import webapp
+from flask import render_template, flash, request, session
+
+from werkzeug.utils import secure_filename
+
+from webapp import xnet
+
+@webapp.route("/", methods = ['GET'])
+def index():
+    # Routine to render the home page of our website
+    return render_template("index.html")
+
+@webapp.route("/predict/", methods = ['GET'])
+def predict():
+    # Routine to route requests from the predict page to display the upload dialog box
+    return render_template("predict.html")
+
+@webapp.route("/upload/", methods = ['POST', 'GET'])
+def upload():
+    # Routine to deal with the uploaded form data i.e. image in this case
+    # Fetches the uploaded image, runs basic validations and saves to the specified directory
+    def __allowed_file(filename):
+        return '.' in filename and \
+            filename.rsplit('.', 1)[1].lower() in webapp.config["ALLOWED_EXTENSIONS"]
+
+    # Clear any existing flash messages from the session
+    session.pop('_flashes', None)
+
+    # Run sanity checks
+    if request.method == 'POST':
+        print("Passed request method sanity check!")
+        # First check whether or not the request contains our desired file
+        if 'file' not in request.files:
+            # Flash an error message and redirect to the same page
+            flash('No file part! Try again!', 'error')
+            return render_template("predict.html")
+
+        print("Passed file exist sanity check!")
+        uploaded_file = request.files['file']
+
+        # Check for the allowed file types and save to the local disk
+        if uploaded_file and __allowed_file(uploaded_file.filename):
+            path = os.path.join(webapp.config['UPLOAD_FOLDER'], 
+                                secure_filename(uploaded_file.filename))
+            uploaded_file.save(path)
+        else:
+            # Flash an error message and redirect to the same page
+            flash('The file must be of one of the accepted formats only! Try again!', 'error')
+            return render_template("predict.html")
+        print("Passed file extension and save check!")
+
+        # Next, run the XNet prediction service
+        result = xnet.predict(webapp.config['XNET_MODEL'], path = path)
+        print("Passed XNet prediction check!")
+        print(result)
+        return render_template("upload.html", filename=uploaded_file.filename, result=result) 

webapp/xnet.py

@@ -0,0 +1,53 @@
+import os
+import cv2
+import numpy as np
+import tensorflow as tf
+from keras.models import model_from_json 
+from tensorflow.keras.optimizers import Adam
+
+def load_model(path:str='model'):
+    # Routine to load the XNet model for inference
+    # Reading the model architecture from the model json file
+    json_file = open(os.path.join(path, 'XNet.json'),'r')
+    loaded_model_json = json_file.read()
+    json_file.close()
+
+    # Use Keras model_from_json to restore the architecture
+    loaded_model = model_from_json(loaded_model_json)
+    print("\nSuccessfully restored model architecture!")
+
+    # Load weights into the reconstructed model
+    loaded_model.load_weights(os.path.join(path, 'XNet.h5'))
+    print("Successfully restored model weights!")
+
+    # Compile and return the loaded model
+    optimizer = Adam(learning_rate=0.0001, decay=1e-5)
+    loaded_model.compile(loss='binary_crossentropy',optimizer=optimizer,metrics=['accuracy'])
+    print("Successfully compiled model!\n")
+
+    return loaded_model
+
+def predict(model, path:str='uploads'):
+    # Transform each stock image into a 224x224 RGB image and 
+    # then into a vector of the same size but normalized between 0 and 1
+    img = cv2.imread(path)
+    img = cv2.resize(img, (224,224))
+
+    if img.shape[2] ==1:
+        img = np.dstack([img, img, img])
+
+    # Normalize the input image and convert into a tensor for inference
+    img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+    img = img.astype(np.float32)/255.
+    X = np.expand_dims(img, axis=0)
+    X = np.array(X)
+    X = tf.convert_to_tensor(X)
+
+    # Run inference
+    y = model.predict(X)
+    file_name = os.path.basename(path)
+    if y[0][0] > 0.5:
+        result = file_name + ' is PNEUMONIA with {}% prediction confidence!'.format(round(y[0][0]*100))
+    else:
+        result = file_name + ' is NORMAL with {}% prediction confidence!'.format(round((1-y[0][0])*100))
+    return result