work on arguments

birdnet_custom_v2.4/model.py

@@ -47,7 +47,7 @@ class Model(ModelBase):
         self,
         default_model_path: str = None,
         model_path: str = None,
-        sensitivity: float = 1.0,
+        sigmoid_sensitivity: float = 1.0,
         num_threads: int = 1,
         **kwargs 
     ):
@@ -58,8 +58,6 @@ class Model(ModelBase):
         classifier_model_path = str(Path(model_path) / "model.tflite")
         classifier_labels_path = str(Path(model_path) / "labels.txt")
 
-        self.sensitivity = sensitivity
-
         # check custom classifier paths through function due to higher complexity
         self._check_classifier_path_integrity(
             classifier_model_path, classifier_labels_path
@@ -71,6 +69,7 @@ class Model(ModelBase):
 
         self.input_layer_index = None
         self.output_layer_index = None
+        self.sigmoid_sensitivity = sigmoid_sensitivity
 
         # use the super class for handling the default models and load the custom ones in this one
         super().__init__(
@@ -78,7 +77,6 @@ class Model(ModelBase):
             model_path=classifier_model_path,
             labels_path=classifier_labels_path,
             num_threads=num_threads,
-            sensitivity=sensitivity,
             **kwargs
         )
 

birdnet_default_v2.4/model.py

@@ -16,7 +16,7 @@ class Model(ModelBase):
         self,
         model_path: str,
         num_threads: int = 1,
-        sensitivity: float = 1.0,
+        sigmoid_sensitivity: float = 1.0,
         species_list_file: str = None,
         **kwargs
     ):
@@ -26,7 +26,7 @@ class Model(ModelBase):
         Args:
             model_path (str): Path to the location of the model file to be loaded
             num_threads (int, optional): Number of threads used for inference. Defaults to 1.
-            sensitivity (float, optional): Parameter of the sigmoid function used to compute probabilities. Defaults to 1.0.
+            sigmoid_sensitivity (float, optional): Parameter of the sigmoid function used to compute probabilities. Defaults to 1.0.
 
         Raises:
             AnalyzerConfigurationError: The model file 'model.tflite' doesn't exist at the given path.
@@ -43,10 +43,11 @@ class Model(ModelBase):
             model_path,
             labels_path,
             num_threads=num_threads,
-            sensitivity=sensitivity,
             **kwargs
         )
 
+        self.sigmoid_sensitivity = sigmoid_sensitivity
+
         # store input and output index to not have to retrieve them each time an inference is made
         input_details = self.model.get_input_details()
 
@@ -84,7 +85,9 @@ class Model(ModelBase):
 
         prediction = self.model.get_tensor(self.output_layer_index)
 
-        confidence = self._sigmoid(np.array(prediction), sensitivity=-self.sensitivity)
+        confidence = self._sigmoid(
+            np.array(prediction), sigmoid_sensitivity=-self.sigmoid_sensitivity
+        )
 
         return confidence
 

google_bird_classification/model.py

@@ -7,7 +7,7 @@ import pandas as pd
 
 class Model(ModelBase):
 
-    def __init__(self, model_path: str, num_threads: int = 1, species_list_file=None, **kwargs):
+    def __init__(self, model_path: str, num_threads: int = 1, **kwargs):
         """
         __init__ Create a new Model instance using the google perch model.
 
@@ -22,12 +22,7 @@ class Model(ModelBase):
         self.class_mask = None  # used later
 
         super().__init__(
-            "google_perch",
-            model_path,
-            labels_path,
-            num_threads=num_threads,
-            **kwargs
-            # sensitivity kwarg doesn't exist here
+            "google_perch", model_path, labels_path, num_threads=num_threads, **kwargs
         )  # num_threads doesn't do anything here.
 
     def predict(self, data: np.array):
@@ -40,10 +35,8 @@ class Model(ModelBase):
             list: List of (label, inferred_probability)
         """
 
-        results = self.labels.copy()
-
         # README: this should be parallelized??
-        logits, embeddings = self.model.infer_tf(
+        logits, _ = self.model.infer_tf(
             np.array(
                 [
                     data,