demo_launching

app.py

@@ -27,43 +27,53 @@ from tensorflow.keras.preprocessing import image as image_utils
 from tensorflow.keras.applications import densenet, efficientnet
 
 
-# load the CNN_binary model
+import tensorflow as tf
+import gradio as gr
+
+# load the CNN binary classification model
 model_cnn = tf.keras.models.load_model("CNN_binary")
 
-# define the labels for the CNN_binary model
+# define the labels for the binary classification model
 labels_cnn = {0: 'healthy', 1: 'Patients'}
 
-# load the efficientNet_binary model
-model_enet = tf.keras.models.load_model("efficientNet_binary")
+# load the EfficientNet binary classification model
+model_efn = tf.keras.models.load_model("efficientNet_binary")
 
-# define the labels for the efficientNet_binary model
-labels_enet = {0: 'healthy', 1: 'Patients'}
+# define the labels for the binary classification model
+labels_efn = {0: 'healthy', 1: 'Patients'}
 
-def classify_image(model, labels, inp):
+def classify_cnn(inp):
     inp = inp.reshape((-1, 224, 224, 3))
     inp = tf.keras.applications.densenet.preprocess_input(inp)
-    prediction = model.predict(inp)
-    confidence = float(prediction[0])
-    return {labels[prediction.argmax()]: confidence}
-
-cnn_interface = gr.Interface(fn=lambda inp: classify_image(model_cnn, labels_cnn, inp),
-                             inputs=gr.inputs.Image(shape=(224, 224)),
-                             outputs=gr.outputs.Label(num_top_classes=2),
-                             title="CNN Binary Image Classification",
-                             description="Classify an image as healthy or patient using CNN binary model.",
-                             #examples=[["patient.jpg"], ["healthy.jpg"]]
-                            )
-
-enet_interface = gr.Interface(fn=lambda inp: classify_image(model_enet, labels_enet, inp),
-                              inputs=gr.inputs.Image(shape=(224, 224)),
-                              outputs=gr.outputs.Label(num_top_classes=2),
-                              title="EfficientNet Binary Image Classification",
-                              description="Classify an image as healthy or patient using EfficientNet binary model.",
-                              #examples=[["patient.jpg"], ["healthy.jpg"]]
-                             )
-
-iface = gr.Interface([cnn_interface, enet_interface],
-                     "tabs",
+    prediction = model_cnn.predict(inp)
+    confidences = {labels_cnn[i]: float(prediction[0][i]) for i in range(2)}
+    return confidences
+
+def classify_efn(inp):
+    inp = inp.reshape((-1, 224, 224, 3))
+    inp = tf.keras.applications.efficientnet.preprocess_input(inp)
+    prediction = model_efn.predict(inp)
+    confidences = {labels_efn[i]: float(prediction[0][i]) for i in range(2)}
+    return confidences
+
+binary_interface_cnn = gr.Interface(fn=classify_cnn, 
+                                inputs=gr.inputs.Image(shape=(224, 224)),
+                                outputs=gr.outputs.Label(num_top_classes=2),
+                                title="CNN Binary Image Classification",
+                                description="Classify an image as healthy or patient using CNN.",
+                                examples=[['300104.png']]
+                               )
+
+binary_interface_efn = gr.Interface(fn=classify_efn, 
+                               inputs=gr.inputs.Image(shape=(224, 224)),
+                               outputs=gr.outputs.Label(num_top_classes=2),
+                               title="EfficientNet Binary Image Classification",
+                               description="Classify an image as healthy or patient using EfficientNet.",
+                               examples=[['300104.png']]
+                              )
+
+demo = gr.Interface([binary_interface_cnn, binary_interface_efn], 
+                     "tab",
                      title="Binary Image Classification",
-                     description="Choose a binary classification model to classify an image as healthy or patient.")
-iface.launch()
+                     description="Classify an image as healthy or patient using either CNN or EfficientNet.")
+demo.launch()