two pages

app.py

@@ -40,42 +40,51 @@ model_binary = tf.keras.models.load_model("densenet")
 # load the multi-label classification model
 model_multi = tf.keras.models.load_model("densenet")
 
+# define the labels for the binary classification model
+labels_binary = {0: 'healthy', 1: 'patient'}
+
 # define the labels for the multi-label classification model
 labels_multi = {0: 'healthy', 1: 'mild', 2: 'moderate'}
 
 
-def classify_image_binary(inp):
-  inp = inp.reshape((-1, 224, 224, 3))
-  inp = tf.keras.applications.densenet.preprocess_input(inp)
-  prediction = model_binary.predict(inp)
-  predicted_class = np.argmax(prediction)
-  confidence = float(prediction[0][predicted_class])
-  label = {0: 'healthy', 1: 'patient'}[predicted_class]
-  return {label: confidence}
-
-def classify_image_multi(inp):
-  inp = inp.reshape((-1, 224, 224, 3))
-  inp = tf.keras.applications.densenet.preprocess_input(inp)
-  prediction = model_multi.predict(inp)
-  confidences = {labels_multi[i]: float(prediction[0][i]) for i in range(len(prediction[0]))}
-  return confidences
-    
-binary_interface = gr.Interface(fn=classify_image_binary, 
-             inputs=gr.inputs.Image(shape=(224, 224)),
-             outputs=gr.outputs.Label(num_top_classes=2),
-             title="Binary Image Classification",
-             description="Classify an image as healthy or patient.",
-             examples=[['300104.png']]
-             )
-
-multi_interface = gr.Interface(fn=classify_image_multi, 
-             inputs=gr.inputs.Image(shape=(224, 224)),
-             outputs=gr.outputs.Label(num_top_classes=3),
-             title="Multi-class Image Classification",
-             description="Classify an image as healthy, mild or moderate.",
-             examples=[['300104.png']]
-             )
-
-binary_interface.launch()
-multi_interface.launch()
+# define the function for the binary classification model
+def classify_binary(inp):
+    inp = inp.reshape((-1, 224, 224, 3))
+    inp = tf.keras.applications.densenet.preprocess_input(inp)
+    prediction = model_binary.predict(inp)
+    confidence = float(prediction[0])
+    label = labels_binary[int(np.round(confidence))]
+    return {label: confidence}
+
+
+# define the function for the multi-label classification model
+def classify_multi(inp):
+    inp = inp.reshape((-1, 224, 224, 3))
+    inp = tf.keras.applications.densenet.preprocess_input(inp)
+    prediction = model_multi.predict(inp)
+    confidences = {labels_multi[i]: float(prediction[0][i]) for i in range(3)}
+    return confidences
+
+
+# create the Gradio interface for the binary classification model
+binary_interface = gr.Interface(fn=classify_binary,
+                                inputs=gr.inputs.Image(shape=(224, 224)),
+                                outputs=gr.outputs.Label(num_top_classes=2),
+                                title="Binary Image Classification",
+                                description="Classify an image as healthy or patient.",
+                                examples=[['300104.png']]
+                                )
+
+# create the Gradio interface for the multi-label classification model
+multi_interface = gr.Interface(fn=classify_multi,
+                               inputs=gr.inputs.Image(shape=(224, 224)),
+                               outputs=gr.outputs.Label(num_top_classes=3),
+                               title="Multi-class Image Classification",
+                               description="Classify an image as healthy, mild or moderate.",
+                               examples=[['300104.png']]
+                               )
+
+# create the Gradio app with both interfaces
+app = gr.Interface([binary_interface, multi_interface], title="Image Classification App")
+app.launch()