Update app.py

app.py

@@ -1,32 +1,38 @@
+# Import libraries
 import gradio as gr
 import tensorflow as tf
 import numpy as np
 
+# Initialize the number of classes, also the image's height and width
 num_classes = 200
 IMG_HEIGHT = 300
 IMG_WIDTH = 300
 
+# Open the classlabel.txt to read the class labels
 with open("classlabel.txt", 'r') as file:
     CLASS_LABEL = [x.strip() for x in file.readlines()]
 
+# Function to normalize the image
 def normalize_image(img):
     img = tf.cast(img, tf.float32) / 255.0
     img = tf.image.resize(img, (IMG_HEIGHT, IMG_WIDTH), method='bilinear')
     return img
 
+# Function to select and load the model
 def load_model(model_name):
     # Load the model based on the model_name input
-    if model_name == 1:
+    if model_name == "Xception":
         return tf.keras.models.load_model("model/Xception.h5")
-    elif model_name == 2:
+    elif model_name == "InceptionV3":
         return tf.keras.models.load_model("model/InceptionV3.h5")
-    elif model_name == 3:
+    elif model_name == "InceptionResNetV2":
         return tf.keras.models.load_model("model/InceptionResNetV2.h5")
-    elif model_name == 4:
+    elif model_name == "DenseNet201":
         return tf.keras.models.load_model("model/DenseNet201.h5")
     else:
         raise ValueError("Invalid model_name")
 
+# Main function, let the model make the prediction on the image uploaded
 def predict_top_classes(img, model_name):
     img = img.convert('RGB')
     img_data = normalize_image(img)
@@ -38,32 +44,24 @@ def predict_top_classes(img, model_name):
     idx = np.argsort(np.squeeze(temp))[::-1]
     top5_value = np.asarray([temp[0][i] for i in idx[0:5]])
     top5_idx = idx[0:5]
-
+    
+    # Return the top 5 highest probability class labels
     return {CLASS_LABEL[i]: str(v) for i, v in zip(top5_idx, top5_value)}
 
-models = {
-    "Xception": 1,
-    "InceptionV3": 2,
-    "InceptionResNetV2": 3,
-    "DenseNet201": 4
-}
-
-def dropdown_example(choice, img):
-    model_name = models[choice]
-    return predict_top_classes(img, model_name)
-
-dropdown = gr.inputs.Dropdown(
-    choices=list(models.keys()),
-    type="index",
-    label="Select a model"
-)
-
-image_input = gr.inputs.Image(type='pil')
-
+# Define the interface
 interface = gr.Interface(
-    fn=dropdown_example,
-    inputs=[dropdown, image_input],
+    predict_top_classes,
+    [
+        gr.inputs.Image(type='pil'),
+        gr.inputs.Dropdown(
+            choices=["Xception","InceptionV3","InceptionResNetV2","DenseNet201"],
+            type="value",
+            label="Select a model",
+            info="Base model that done feature extraction and fine-tuning process"
+        )
+    ]
     outputs='label'
 )
-
+    
+# Launch the interface
 interface.launch()