add noise

nnet/augmentation.py

@@ -489,8 +489,9 @@ def data_augmentation(speech,
         speech = torch.nn.functional.conv1d(speech_[None, ...], rir[None, ...])[0]
 
     if "add_noise" in augmentations:
-        # Pick a noise sample from the noise_df
-        noise_row = noise_df.iloc[random.randrange(noise_df.shape[0])]
+        # Pick a noise type
+        noise = torch.zeros_like(speech)
+        noise_idx = random.randrange(3)
 
         # speech
         if noise_idx == 0:

nnet/xvector.py

@@ -202,7 +202,10 @@ def eer(negatives, positives):
 
 def test_metrics(model,
                  device,
-                 speaker_number,
+                 idmap_test_filename,
+                 ndx_test_filename,
+                 key_test_filename,
+                 data_root_name,
                  num_thread,
                  mixed_precision):
     """Compute model metrics
@@ -221,10 +224,10 @@ def test_metrics(model,
     Returns:
         [type]: [description]
     """
-    idmap_test_filename = 'h5f/idmap_test.h5'
-    ndx_test_filename = 'h5f/ndx_test.h5'
-    key_test_filename = 'h5f/key_test.h5'
-    data_root_name='/lium/scratch/larcher/voxceleb1/test/wav'
+    #idmap_test_filename = 'h5f/idmap_test.h5'
+    #ndx_test_filename = 'h5f/ndx_test.h5'
+    #key_test_filename = 'h5f/key_test.h5'
+    #data_root_name='/lium/scratch/larcher/voxceleb1/test/wav'
 
     transform_pipeline = dict()
 
@@ -837,7 +840,6 @@ def xtrain(speaker_number,
             new_model_dict.update(pretrained_dict)
             model.load_state_dict(new_model_dict)
 
-
         # Freeze required layers
         for name, param in model.named_parameters():
             if name.split(".")[0] in freeze_parts:
@@ -980,7 +982,7 @@ def xtrain(speaker_number,
     elif opt == 'rmsprop':
         _optimizer = torch.optim.RMSprop
         _options = {'lr': lr}
-    else: # opt == 'sgd'
+    else:  # opt == 'sgd'
         _optimizer = torch.optim.SGD
         _options = {'lr': lr, 'momentum': 0.9}
 
@@ -1002,9 +1004,9 @@ def xtrain(speaker_number,
         param_list.append({'params': model.module.after_speaker_embedding.parameters(), 'weight_decay': model.module.after_speaker_embedding_weight_decay})
 
     optimizer = _optimizer(param_list, **_options)
-    scheduler = scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, 
-                                                                 milestones=[10000,50000,100000], 
-                                                                 gamma=0.5)
+    scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer,
+                                                     milestones=[10000,50000,100000],
+                                                     gamma=0.5)
 
     if mixed_precision:
         scaler = torch.cuda.amp.GradScaler()
@@ -1047,7 +1049,15 @@ def xtrain(speaker_number,
             logging.critical(f"***{time.strftime('%H:%M:%S', time.localtime())} Training metrics - Cross validation accuracy = {val_acc} %, EER = {val_eer * 100} %")
 
             if compute_test_eer:
-                test_eer = test_metrics(model, device, speaker_number, num_thread, mixed_precision)
+                test_eer = test_metrics(model,
+                                        device,
+                                        idmap_test_filename=dataset_params["test_set"]["idmap_test_filename"],
+                                        ndx_test_filename=dataset_params["test_set"]["ndx_test_filename"],
+                                        key_test_filename=dataset_params["test_set"]["key_test_filename"],
+                                        data_root_name=dataset_params["test_set"]["data_root_name"],
+                                        num_thread=num_thread,
+                                        mixed_precision=mixed_precision)
+
                 logging.critical(f"***{time.strftime('%H:%M:%S', time.localtime())} Training metrics - Test EER = {test_eer * 100} %")
 
             # remember best accuracy and save checkpoint