cast to float

app.py

@@ -33,7 +33,7 @@ def create_model(input_shape):
 def soft_quantized_influence_measure_sigmoid(
     y_true: tf.Tensor, y_pred: tf.Tensor, threshold: float = 0.5
 ) -> tf.Tensor:
-    # Cast y_true and y_pred to float32 to ensure compatibility with tf operations
+    # Ensure y_true and y_pred are of type float32
     y_true = tf.cast(y_true, tf.float32)
     y_pred = tf.cast(y_pred, tf.float32)
 
@@ -56,11 +56,16 @@ def soft_quantized_influence_measure_sigmoid(
     true_error_loss = tf.square(error) * tf.square(n1)
     false_error_loss = tf.square(error) * tf.square(n2)
 
-    # Apply weights to errors based on whether they are small or large, and normalize the final loss
+    # Ensure the losses are of the same type as the condition in tf.where
+    true_error_loss = tf.cast(true_error_loss, tf.float32)
+    false_error_loss = tf.cast(false_error_loss, tf.float32)
+
+    # Apply weights to errors based on whether they are small or large
     final_loss = tf.where(is_small_error, true_error_loss, false_error_loss)
-    final_loss = (
-        tf.reduce_mean(final_loss) / tf.square(y_std) ** 2 / len(y_true)
-    )  # Normalize by the square of the standard deviation of true values
+
+    # Normalize the final loss - ensure division is properly handled with float types
+    num_elements = tf.cast(tf.size(y_true), tf.float32)  # Cast number of elements to float
+    final_loss = tf.reduce_mean(final_loss) / tf.square(y_std) ** 2 / num_elements
 
     return final_loss