Create app.py

app.py

@@ -0,0 +1,75 @@
+import gradio as gr
+
+from timeit import default_timer as timer
+from model import create_effnetb2_model
+from typing import Tuple , Dict
+import tensorflow as tf 
+import numpy as np
+
+from PIL import Image
+import os
+
+# 1.Import and class names setup
+class_names = []
+
+
+# 2. Model annd transforms prepration
+model = tf.keras.models.load_model(
+    'best_model_lg.keras', custom_objects=None, compile=True, safe_mode=True
+)
+
+# Load save weights
+
+# 3.prediction function (predict())
+
+def load_and_prep_imgg(filename, img_shape=224, scale=True):
+    img = tf.io.read_file(filename)
+    img = tf.io.decode_image(img)
+    img = tf.image.resize(img, size=[img_shape, img_shape])
+    if scale:
+        return img / 255
+    else:
+        return img
+        
+def predict(img) -> Tuple[Dict,float] :
+
+  start_time = timer()
+
+  image =  load_and_prep_imgg(img)
+  image = Image.open(image)  
+
+  pred_img = model.predict(tf.expand_dims(img, axis=0))
+  pred_class = class_names[pred_img.argmax()]
+  st.write(f"Predicted brain tumor is: {pred_class} with probability: {pred_img.max():.2f}")
+
+  
+
+  
+  end_time = timer()
+  pred_time = round(end_time - start_time , 4)
+
+  return pred_class , pred_time
+
+### 4. Gradio app - our Gradio interface + launch command
+
+title = 'FoodVision Big'
+description = 'Feature Extraxtion VGG  model to classifiy Macular Diseases by OCT '
+article = 'created at Tensorflow Model Deployment'
+
+# Create example list
+
+example_list = [['examples/'+ example] for example in os.listdir('examples')]
+example_list
+
+# create a gradio demo
+demo = gr.Interface(fn=predict ,
+                    inputs=gr.Image(type='pil'),
+                    outputs=[gr.Label(num_top_classes = 3 , label= 'prediction'),
+                            gr.Number(label= 'Prediction time (s)')],
+                    examples = example_list,
+                    title = title,
+                    description = description,
+                    article= article)
+
+# Launch the demo
+demo.launch(debug= False)