Create app.py

app.py

@@ -0,0 +1,48 @@
+import gradio as gr
+import tensorflow as tf
+import numpy as np
+import os
+import tensorflow as tf
+import numpy as np
+from keras.models import load_model
+from tensorflow.keras.utils import load_img
+
+# Charger le modèle
+
+model = load_model('model_multi.h5')
+
+
+def format_decimal(value):
+    decimal_value = format(value, ".2f")
+    return decimal_value
+    
+def detect(img):
+    img = np.expand_dims(img, axis=0)
+    img = img/255
+    prediction = model.predict(img)[0]
+    #     if prediction[0] <= 0.80:
+    #     return "Pneumonia  Detected!"
+
+    # return "Pneumonia Not Detected!"
+    if format_decimal(prediction[0]) >= "0.5":
+        return "Risque d'infection bactérienne"
+    if format_decimal(prediction[1]) >= "0.5":
+        return "Poumon sain"
+    if format_decimal(prediction[2]) >= "0.5":
+        return "Risque d'infection biologique"
+
+
+# result = detect(img)
+# print(result)
+os.system("tar -zxvf examples.tar.gz")
+examples = ['examples/n1.jpeg', 'examples/n2.jpeg', 'examples/n3.jpeg', 'examples/n4.jpeg', 'examples/n5.jpeg',
+            'examples/n6.jpeg', 'examples/n7.jpeg', 'examples/n8.jpeg', 'examples/p6.jpeg', 'examples/p7.jpeg',]
+
+input = gr.inputs.Image(shape=(100,100))
+
+
+
+title = "PneumoDetect: Pneumonia Detection from Chest X-Rays"
+
+iface = gr.Interface(fn=detect, inputs=input, outputs="text",examples = examples, examples_per_page=20, title=title)
+iface.launch(inline=False)