Update api.py

api.py

@@ -30,6 +30,7 @@ from sklearn.svm import SVC
 import joblib
 
 model = tf.keras.models.load_model('946_.keras', compile=False)
+modelPalm = tf.keras.models.load_model('palm_model.h5', compile=False)
 
 file_path = "Algeria Plant Disease Treatment Plan.docx"
 def docx_to_knowledge_base(file_path):
@@ -287,6 +288,63 @@ async def classify(image: UploadFile = File(...)):
         return {"prediction": predicted_class_idx,"gradcam": base64_image,"ration":ratio}
     else:
         return {"error": "No image provided"}
+
+
+def make_gradcam_heatmap_Palm(img_array, model, base_model_name, last_conv_layer_name, pred_index=None):
+    base_model = model.get_layer(base_model_name)
+    last_conv_layer = base_model.get_layer(last_conv_layer_name)
+
+    grad_model = tf.keras.models.Model(
+        inputs=[model.inputs],
+        outputs=[last_conv_layer.output, model.output]
+    )
+
+    with tf.GradientTape() as tape:
+        conv_outputs, predictions = grad_model(img_array)
+        if pred_index is None:
+            pred_index = tf.argmax(predictions[0])
+        loss = predictions[:, pred_index]
+
+    grads = tape.gradient(loss, conv_outputs)
+    pooled_grads = tf.reduce_mean(grads, axis=(0, 1, 2))
+    conv_outputs = conv_outputs[0]
+    heatmap = conv_outputs @ pooled_grads[..., tf.newaxis]
+    heatmap = tf.squeeze(heatmap)
+    heatmap = tf.maximum(heatmap, 0) / tf.math.reduce_max(heatmap)
+    return heatmap.numpy()
+
+
+@app.post("/palmclassify")
+async def palmclassify(image: UploadFile = File(...)):
+    if image is not None:
+        img = Image.open(io.BytesIO(await image.read()))
+        img = img.resize((64,64))
+        img_array = np.array(img) / 255.0
+        img_array = np.expand_dims(img_array, axis=0)
+        predictions = modelPalm.predict(img_array)
+        predicted_class_idx = np.argmax(predictions)
+        predicted_class_idx = int(predicted_class_idx)
+
+        last_mb = "Conv_1"
+
+        # heatmap = make_gradcam_heatmap(img_array, modelPalm, last_mb)
+        heatmap = make_gradcam_heatmap_Palm(
+            img_array,
+            modelPalm,
+            base_model_name='mobilenetv2_1.00_224',
+            last_conv_layer_name='Conv_1'
+        )
+
+        base64_image = display_gradcam( np.array(img), heatmap)
+        
+        # Return the base64 encoded image in the response
+
+        # Calculate and print the activation ratio
+        ratio = calculate_activation_ratio(heatmap)
+        
+        return {"prediction": predicted_class_idx,"gradcam": base64_image,"ration":ratio}
+    else:
+        return {"error": "No image provided"}
         
 
 yolomodel = YOLO("yolo11m.pt")