diff --git a/monai/transforms/intensity/array.py b/monai/transforms/intensity/array.py
index 0e9f922888..2dc1ed1a94 100644
--- a/monai/transforms/intensity/array.py
+++ b/monai/transforms/intensity/array.py
@@ -739,7 +739,8 @@ def __call__(self, img: NdarrayOrTensor) -> NdarrayOrTensor:
         epsilon = 1e-7
         img_min = img.min()
         img_range = img.max() - img_min
-        return ((img - img_min) / float(img_range + epsilon)) ** self.gamma * img_range + img_min
+        ret: NdarrayOrTensor = ((img - img_min) / float(img_range + epsilon)) ** self.gamma * img_range + img_min
+        return ret
 
 
 class RandAdjustContrast(RandomizableTransform):
diff --git a/monai/transforms/spatial/array.py b/monai/transforms/spatial/array.py
index 62ac5d2c3e..27d25cf2bc 100644
--- a/monai/transforms/spatial/array.py
+++ b/monai/transforms/spatial/array.py
@@ -13,7 +13,6 @@
 https://github.com/Project-MONAI/MONAI/wiki/MONAI_Design
 """
 import warnings
-from copy import deepcopy
 from typing import Any, List, Optional, Sequence, Tuple, Union
 
 import numpy as np
@@ -200,9 +199,8 @@ def __call__(
 
         # no resampling if it's identity transform
         if np.allclose(transform, np.diag(np.ones(len(transform))), atol=1e-3):
-            output_data, *_ = convert_data_type(deepcopy(data_array), dtype=_dtype)
+            output_data, *_ = convert_data_type(data_array, dtype=torch.float32)
             new_affine = to_affine_nd(affine, new_affine)  # type: ignore
-
         else:
             # resample
             affine_xform = AffineTransform(
@@ -220,7 +218,7 @@ def __call__(
                 convert_data_type(transform, torch.Tensor, data_array_t.device, dtype=_dtype)[0],
                 spatial_size=output_shape if output_spatial_shape is None else output_spatial_shape,
             ).squeeze(0)
-            output_data, *_ = convert_to_dst_type(output_data, data_array, dtype=_dtype)
+            output_data, *_ = convert_to_dst_type(output_data, data_array, dtype=torch.float32)
             new_affine = to_affine_nd(affine, new_affine)  # type: ignore
 
         return output_data, affine, new_affine