diff --git a/dosma/core/numpy_routines.py b/dosma/core/numpy_routines.py
index a96e9a4..b887d64 100644
--- a/dosma/core/numpy_routines.py
+++ b/dosma/core/numpy_routines.py
@@ -161,7 +161,7 @@ def nan_to_num(x, copy=True, nan=0.0, posinf=None, neginf=None):
         return x._partial_clone(volume=vol)
 
 
-@implements(np.around, np.round, np.round_)
+@implements(np.around, np.round, np.round)
 def around(x, decimals=0, affine=False):
     """Round medical image pixel data (and optionally affine) to the given number of decimals.
 
diff --git a/dosma/models/model_loading_util.py b/dosma/models/model_loading_util.py
index 55c7310..faad8a7 100644
--- a/dosma/models/model_loading_util.py
+++ b/dosma/models/model_loading_util.py
@@ -72,7 +72,7 @@ def _gen_mask(func, *_args, **_kwargs):
 
     if isinstance(cfg_file_or_dict, str):
         with open(cfg_file_or_dict, "r") as f:
-            cfg = yaml.load(f)
+            cfg = yaml.load(f, Loader=yaml.FullLoader)
     else:
         cfg = cfg_file_or_dict
 
diff --git a/dosma/models/oaiunet2d.py b/dosma/models/oaiunet2d.py
index 5a919f7..05fba69 100644
--- a/dosma/models/oaiunet2d.py
+++ b/dosma/models/oaiunet2d.py
@@ -79,6 +79,7 @@ def __load_keras_model__(self, input_shape, force_weights=False):
                 padding="same",
                 activation="relu",
                 kernel_initializer="he_normal",
+                name=f"conv2d_down_{depth_cnt}_1"  # Unique name for each layer
             )(pool)
             conv = Conv2D(
                 nfeatures[depth_cnt],
@@ -86,6 +87,7 @@ def __load_keras_model__(self, input_shape, force_weights=False):
                 padding="same",
                 activation="relu",
                 kernel_initializer="he_normal",
+                name=f"conv2d_down_{depth_cnt}_2"  # Unique name for each layer
             )(conv)
 
             conv = BN(axis=-1, momentum=0.95, epsilon=0.001)(conv)
@@ -134,6 +136,7 @@ def __load_keras_model__(self, input_shape, force_weights=False):
                 padding="same",
                 activation="relu",
                 kernel_initializer="he_normal",
+                name=f"conv2d_up_{depth_cnt}_1"  # Unique name for each layer
             )(up)
             conv = Conv2D(
                 nfeatures[depth_cnt],
@@ -141,6 +144,7 @@ def __load_keras_model__(self, input_shape, force_weights=False):
                 padding="same",
                 activation="relu",
                 kernel_initializer="he_normal",
+                name=f"conv2d_up_{depth_cnt}_2"  # Unique name for each layer
             )(conv)
 
             conv = BN(axis=-1, momentum=0.95, epsilon=0.001)(conv)
diff --git a/dosma/scan_sequences/mri/qdess.py b/dosma/scan_sequences/mri/qdess.py
index a308a39..341c864 100644
--- a/dosma/scan_sequences/mri/qdess.py
+++ b/dosma/scan_sequences/mri/qdess.py
@@ -107,6 +107,7 @@ def generate_t2_map(
         tissue: Tissue = None,
         suppress_fat: bool = False,
         suppress_fluid: bool = False,
+        b1map: MedicalVolume = None,
         beta: float = 1.2,
         gl_area: float = None,
         tg: float = None,
@@ -211,9 +212,16 @@ def generate_t2_map(
 
         # Flip Angle (degree -> radians)
         alpha = float(ref_dicom.FlipAngle) if alpha is None else alpha
-        alpha = math.radians(alpha)
-        if np.allclose(math.sin(alpha / 2), 0):
-            warnings.warn("sin(flip angle) is close to 0 - t2 map may fail.", stacklevel=2)
+
+        if b1map:
+            alpha_nominal = deepcopy(alpha)
+            alpha = np.multiply(b1map.volume, math.radians(alpha))
+            if np.allclose(np.sin(alpha_nominal / 2), 0):
+                warnings.warn("sin(flip angle) is close to 0 - t2 map may fail.")
+        else:
+            alpha = math.radians(alpha)
+            if np.allclose(math.sin(alpha / 2), 0):
+                warnings.warn("sin(flip angle) is close to 0 - t2 map may fail.")
 
         mask = xp.ones([r, c, num_slices])
 
@@ -244,7 +252,7 @@ def generate_t2_map(
                 / (1 - xp.cos(alpha) * xp.exp(-TR / T1))
             )
             c1 = 0 
-        
+
         # have to divide division into steps to avoid overflow error
         t2map = -2000 * (TR - TE) / (xp.log(abs(ratio) / k) + c1)
         t2map = xp.nan_to_num(t2map)