Update app.py

app.py

@@ -1,14 +1,11 @@
 import numpy as np
 import gradio as gr
-import tensorflow as tf #version 2.13.0
-import keras #version 
-import numpy as np
+import tensorflow as tf  # version 2.13.0
+from keras.models import load_model  # version matching your TensorFlow
 import cv2
-import tensorflow as tf
-import h5py
-def analyse(img,plant_type):
-    import json
+import json
 
+def analyse(img, plant_type):
     # Load label_disease.json
     with open('data/label_disease.json', 'r') as f:
         label_disease = json.load(f)
@@ -16,41 +13,60 @@ def analyse(img,plant_type):
     # Load plant_label_disease.json
     with open('data/plant_label_disease.json', 'r') as f:
         plant_label_disease = json.load(f)
-    print(label_disease,label_disease["34"])
+
     HEIGHT = 256
     WIDTH = 256
-    modelArchitecturePath ='model/model_architecture.h5'
+    modelArchitecturePath = 'model/model_architecture.h5'
     modelWeightsPath = 'model/model_weights.h5'
-    dnn_model = keras.models.load_model(modelArchitecturePath,compile=False)
+
+    # Load the model
+    dnn_model = load_model(modelArchitecturePath, compile=False)
     dnn_model.load_weights(modelWeightsPath)
-    
-    process_img = cv2.resize(img, (HEIGHT, WIDTH),interpolation = cv2.INTER_LINEAR)
-    process_img = process_img/(255)
+
+    # Preprocess the image
+    process_img = cv2.resize(img, (HEIGHT, WIDTH), interpolation=cv2.INTER_LINEAR)
+    process_img = process_img / 255.0
     process_img = np.expand_dims(process_img, axis=0)
-    
-    
+
+    # Predict using the model
     y_pred = dnn_model.predict(process_img)
     y_pred = y_pred[0]
-    print("y pred",y_pred)
-    
+
+    # Identify predictions
     p_id = plant_label_disease[plant_type.lower()][0]
-    
     for disease in plant_label_disease[plant_type.lower()]:
-            if y_pred[disease] > y_pred[p_id]:
-                p_id = disease
-    
+        if y_pred[disease] > y_pred[p_id]:
+            p_id = disease
+
     overall_predicted_id = np.argmax(y_pred)
     overall_predicted_name = label_disease[str(overall_predicted_id)]
     overall_predicted_acc = y_pred[overall_predicted_id]
-    
-    plant_predicted_id =p_id
+
+    plant_predicted_id = p_id
     plant_predicted_name = label_disease[str(plant_predicted_id)]
     plant_predicted_acc = y_pred[plant_predicted_id]
-    
-    return plant_predicted_id, plant_predicted_name, plant_predicted_acc, overall_predicted_id, overall_predicted_name, overall_predicted_acc
-
-demo = gr.Interface(analyse, 
-                    [gr.Image(),gr.Radio(["Apple","Blueberry","Cherry","Corn","Grape","Orange","Peach","Pepper","Potato","Raspberry","Soybean","Squash","Strawberry","Tomato"])],
-                    ["number","text","number","number","text","number"],
-                   )
-demo.launch(share=True,show_error=True)
+
+    # Return results as a JSON object
+    result = {
+        "plant_predicted_id": int(plant_predicted_id),
+        "plant_predicted_name": plant_predicted_name,
+        "plant_predicted_accuracy": float(plant_predicted_acc),
+        "overall_predicted_id": int(overall_predicted_id),
+        "overall_predicted_name": overall_predicted_name,
+        "overall_predicted_accuracy": float(overall_predicted_acc),
+    }
+
+    return result
+
+# Gradio interface
+demo = gr.Interface(
+    fn=analyse,
+    inputs=[
+        gr.Image(type="numpy"),
+        gr.Radio(["Apple", "Blueberry", "Cherry", "Corn", "Grape", "Orange", "Peach",
+                  "Pepper", "Potato", "Raspberry", "Soybean", "Squash", "Strawberry", "Tomato"])
+    ],
+    outputs=gr.JSON()
+)
+
+demo.launch(share=True, show_error=True)