Update app.py

app.py

@@ -1,47 +1,28 @@
 import gradio as gr
+from transformers import pipeline
 import numpy as np
 from PIL import Image
 import tensorflow as tf
-import os
 
-# Print the current working directory
-print("Current working directory:", os.getcwd())
-
-# Update this to the correct path of your model
-model_path = r'./model12acc99_kera.h5'
-
-# Custom object configuration handling
-def custom_separable_conv2d(**kwargs):
-    # Remove unsupported parameters if they exist
-    kwargs.pop('kernel_initializer', None)
-    kwargs.pop('kernel_regularizer', None)
-    kwargs.pop('kernel_constraint', None)
-    return tf.keras.layers.SeparableConv2D(**kwargs)
-
-# Register custom object
-custom_objects = {'SeparableConv2D': custom_separable_conv2d}
-
-# Check if the file exists
-if not os.path.exists(model_path):
-    raise FileNotFoundError(f"Model file not found at {model_path}")
-
-# Load the model with custom objects
-model_h5 = tf.keras.models.load_model(model_path, custom_objects=custom_objects)
+model_path = r'./model12_acc99_kera.h5'
 
 # Function to preprocess the image and make predictions
-def classify_Lung_and_colon_image(input_image):
+def classify_lung_and_colon(input_image):
     try:
         # Preprocess the image (resize, normalize, etc.)
         input_image = np.array(input_image)
-        input_image_resized = np.array(Image.fromarray(input_image).resize((224, 224))) / 255.0
+        input_image_copy = input_image.copy()  # Making a copy to avoid the array reference issue
+        input_image_resized = np.array(Image.fromarray(input_image_copy).resize((228,228))) 
+        # / 255.0
         input_image_resized = np.expand_dims(input_image_resized, axis=0)
 
         # Making predictions
+        model_h5 = tf.keras.models.load_model(model_path)
         predictions = model_h5.predict(input_image_resized)
 
         # Getting the class with the highest probability
         class_idx = np.argmax(predictions)
-        class_label = ["Colon Adenocarcinoma", "Colon Benign Tissue", "Lung Adenocarcinoma", "Lung Benign Tissue", "Lung Squamous Cell Carcinoma"][class_idx]
+        class_label = ["Colon Adenocarcinoma", "Colon Benign Tissue", "Lung Adenocarcinoma", "Lung Benign Tissue","Lung Squamous Cell Carcinoma"][class_idx]
         confidence = predictions[0][class_idx]
 
         return f"Prediction: {class_label}, Confidence: {confidence:.2f}"
@@ -50,14 +31,14 @@ def classify_Lung_and_colon_image(input_image):
 
 # Creating a Gradio interface
 iface = gr.Interface(
-    fn=classify_Lung_and_colon_image,
+    fn=classify_lung_and_colon,
     inputs="image",
     outputs="text",
     title="Lung and Colon Cancer Detection",
-    description="Upload a Histopathology Image for classification.",
-    flagging_options=["wrongPrediction"],
-    theme='default'  # Changed theme to 'default' for compatibility
+    description="Upload a Histopathology Image",
+    flagging_options = ["Wrong Prediction"],
+    theme = 'darkhuggingface'
 )
 
 # Launching the Gradio interface
-iface.launch(inline=False)
+iface.launch(inline = False)