API tuning

nnet/xvector.py

@@ -314,7 +314,7 @@ class TrainingMonitor():
         """
         # TODO
         self.logger.critical(f"***Validation metrics - Cross validation accuracy = {self.val_acc[-1]} %, EER = {self.val_eer[-1] * 100} %")
-        #self.logger.critical(f"***Test metrics - Test EER = {self.test_eer[-1] * 100} %")
+        self.logger.critical(f"***Test metrics - Test EER = {self.test_eer[-1] * 100} %")
 
     def display_final(self):
         """
@@ -1006,10 +1006,10 @@ def get_network(model_opts, local_rank):
     """
 
     if model_opts["model_type"] in ["xvector", "rawnet2", "resnet34", "fastresnet34", "halfresnet34"]:
-        model = Xtractor(model_opts["speaker_number"], model_opts["model_type"], loss=model_opts["loss"]["type"])
+        model = Xtractor(model_opts["speaker_number"], model_opts["model_type"], loss=model_opts["loss"]["type"], embedding_size=model_opts["embedding_size"])
     else:
         # Custom type of model
-        model = Xtractor(model_opts["speaker_number"], model_opts, loss=model_opts["loss"]["type"])
+        model = Xtractor(model_opts["speaker_number"], model_opts, loss=model_opts["loss"]["type"], embedding_size=model_opts["embedding_size"])
 
     # Load the model if it exists
     if model_opts["initial_model_name"] is not None and os.path.isfile(model_opts["initial_model_name"]):