model_binary_two

app.py

@@ -23,55 +23,56 @@ from torchvision.transforms import functional as F
 import numpy as np
 import tensorflow as tf
 from transformers import pipeline
+from tensorflow.keras.preprocessing import image as image_utils
+from tensorflow.keras.applications import densenet, efficientnet
 
 
 # load the binary classification model
-model_binary = tf.keras.models.load_model("CNN_binary")
-
-# define the labels for the binary classification model
-labels_binary = {0: 'healthy', 1: 'Patients'}
-
-# load the multi-label classification model
-model_multi = tf.keras.models.load_model("CNN_multiclass")
+model_cnn = tf.keras.models.load_model("CNN_binary")
+model_efficientnet = tf.keras.models.load_model("EfficientNet_binary")
 
 # define the labels for the multi-label classification model
-labels_multi = {0: 'healthy', 1: 'mild', 2: 'moderate'}
-
-def classify_binary(inp):
-    inp = inp.reshape((-1, 224, 224, 3))
-    inp = tf.keras.applications.densenet.preprocess_input(inp)
-    prediction = model_binary.predict(inp)
+labels_cnn = {0: 'healthy', 1: 'patient'}
+labels_efficientnet = {0: 'healthy', 1: 'patient'}
+
+def classify_cnn(inp):
+    img = np.array(inp)
+    img = img.reshape((1, 224, 224, 3))
+    img = densenet.preprocess_input(img)
+    prediction = model_cnn.predict(img)
     confidence = float(prediction[0])
-    return {labels_binary[prediction.argmax()]: confidence}
-
-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(len(labels_multi))}
-    return confidences
-
-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']]
-                               )
+    return {labels_cnn[prediction.argmax()]: confidence}
 
-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']]
-                              )
-
-demo = gr.Interface([binary_interface, multi_interface], 
+def classify_efficientnet(inp):
+    img = np.array(inp)
+    img = img.reshape((1, 224, 224, 3))
+    img = efficientnet.preprocess_input(img)
+    prediction = model_efficientnet.predict(img)
+    confidence = float(prediction[0])
+    return {labels_efficientnet[prediction.argmax()]: confidence}
+
+cnn_interface = 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 a CNN model.",
+                             examples=[['300104.png']]
+                            )
+
+efficientnet_interface = gr.Interface(fn=classify_efficientnet, 
+                                       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 an EfficientNet model.",
+                                       examples=[['300104.png']]
+                                      )
+# create a combined interface with tabs for each binary classification model
+demo = gr.Interface([cnn_interface, efficientnet_interface], 
                      "tab",
-                     title="Binary and Multi-class Image Classification",
-                     description="Classify an image as healthy, mild or moderate.")
-demo.launch()
+                     title="Binary Image Classification",
+                     description="Classify an image as healthy or patient using different binary classification models."
+                    )
 
+demo.launch()