From df1e988eaa9986689337f01e79ae13181e585188 Mon Sep 17 00:00:00 2001
From: jirka <jirka.borovec@seznam.cz>
Date: Thu, 29 Aug 2024 22:42:34 +0200
Subject: [PATCH 01/11] tests: move reset seed to fixture

---
 src/torchmetrics/image/_deprecated.py         | 47 ++++++++---------
 src/torchmetrics/image/d_lambda.py            | 21 ++++----
 src/torchmetrics/image/d_s.py                 | 27 +++++-----
 src/torchmetrics/image/ergas.py               | 14 +++---
 src/torchmetrics/image/fid.py                 |  5 +-
 src/torchmetrics/image/inception.py           |  5 +-
 src/torchmetrics/image/kid.py                 |  9 ++--
 src/torchmetrics/image/lpip.py                |  9 ++--
 src/torchmetrics/image/mifid.py               |  7 ++-
 .../image/perceptual_path_length.py           | 11 ++--
 src/torchmetrics/image/psnrb.py               |  8 ++-
 src/torchmetrics/image/qnr.py                 | 27 +++++-----
 src/torchmetrics/image/rase.py                | 15 +++---
 src/torchmetrics/image/rmse_sw.py             |  8 +--
 src/torchmetrics/image/sam.py                 | 21 ++++----
 src/torchmetrics/image/scc.py                 |  7 ++-
 src/torchmetrics/image/ssim.py                | 13 +++--
 src/torchmetrics/image/tv.py                  |  3 +-
 src/torchmetrics/image/vif.py                 |  7 ++-
 src/torchmetrics/multimodal/clip_iqa.py       | 15 +++---
 src/torchmetrics/multimodal/clip_score.py     |  4 +-
 src/torchmetrics/nominal/cramers.py           |  6 +--
 src/torchmetrics/nominal/fleiss_kappa.py      | 12 ++---
 src/torchmetrics/nominal/pearson.py           |  6 +--
 src/torchmetrics/nominal/theils_u.py          |  6 +--
 src/torchmetrics/nominal/tschuprows.py        |  6 +--
 src/torchmetrics/regression/wmape.py          |  7 ++-
 .../segmentation/generalized_dice.py          | 13 +++--
 src/torchmetrics/segmentation/mean_iou.py     | 13 +++--
 src/torchmetrics/text/_deprecated.py          |  7 ++-
 src/torchmetrics/text/perplexity.py           |  7 ++-
 src/torchmetrics/wrappers/bootstrapping.py    |  6 +--
 src/torchmetrics/wrappers/classwise.py        | 50 +++++++++----------
 src/torchmetrics/wrappers/feature_share.py    |  1 -
 src/torchmetrics/wrappers/tracker.py          | 30 ++++++-----
 35 files changed, 202 insertions(+), 251 deletions(-)

diff --git a/src/torchmetrics/image/_deprecated.py b/src/torchmetrics/image/_deprecated.py
index 597f0a0c636..86fb04c7f1c 100644
--- a/src/torchmetrics/image/_deprecated.py
+++ b/src/torchmetrics/image/_deprecated.py
@@ -17,11 +17,11 @@
 class _ErrorRelativeGlobalDimensionlessSynthesis(ErrorRelativeGlobalDimensionlessSynthesis):
     """Wrapper for deprecated import.
 
-    >>> import torch
-    >>> preds = torch.rand([16, 1, 16, 16], generator=torch.manual_seed(42))
+    >>> from torch import rand
+    >>> preds = rand([16, 1, 16, 16])
     >>> target = preds * 0.75
     >>> ergas = _ErrorRelativeGlobalDimensionlessSynthesis()
-    >>> torch.round(ergas(preds, target))
+    >>> ergas(preds, target).round()
     tensor(10.)
 
     """
@@ -39,8 +39,8 @@ def __init__(
 class _MultiScaleStructuralSimilarityIndexMeasure(MultiScaleStructuralSimilarityIndexMeasure):
     """Wrapper for deprecated import.
 
-    >>> import torch
-    >>> preds = torch.rand([3, 3, 256, 256], generator=torch.manual_seed(42))
+    >>> from torch import rand
+    >>> preds = rand([3, 3, 256, 256])
     >>> target = preds * 0.75
     >>> ms_ssim = _MultiScaleStructuralSimilarityIndexMeasure(data_range=1.0)
     >>> ms_ssim(preds, target)
@@ -103,13 +103,12 @@ def __init__(
 class _RelativeAverageSpectralError(RelativeAverageSpectralError):
     """Wrapper for deprecated import.
 
-    >>> import torch
-    >>> g = torch.manual_seed(22)
-    >>> preds = torch.rand(4, 3, 16, 16)
-    >>> target = torch.rand(4, 3, 16, 16)
+    >>> from torch import rand
+    >>> preds = rand(4, 3, 16, 16)
+    >>> target = rand(4, 3, 16, 16)
     >>> rase = _RelativeAverageSpectralError()
     >>> rase(preds, target)
-    tensor(5114.66...)
+    tensor(5326.40...)
 
     """
 
@@ -125,13 +124,12 @@ def __init__(
 class _RootMeanSquaredErrorUsingSlidingWindow(RootMeanSquaredErrorUsingSlidingWindow):
     """Wrapper for deprecated import.
 
-    >>> import torch
-    >>> g = torch.manual_seed(22)
-    >>> preds = torch.rand(4, 3, 16, 16)
-    >>> target = torch.rand(4, 3, 16, 16)
+    >>> from torch import rand
+    >>> preds = rand(4, 3, 16, 16)
+    >>> target = rand(4, 3, 16, 16)
     >>> rmse_sw = RootMeanSquaredErrorUsingSlidingWindow()
     >>> rmse_sw(preds, target)
-    tensor(0.3999)
+    tensor(0.4158)
 
     """
 
@@ -147,10 +145,9 @@ def __init__(
 class _SpectralAngleMapper(SpectralAngleMapper):
     """Wrapper for deprecated import.
 
-    >>> import torch
-    >>> gen = torch.manual_seed(42)
-    >>> preds = torch.rand([16, 3, 16, 16], generator=gen)
-    >>> target = torch.rand([16, 3, 16, 16], generator=gen)
+    >>> from torch import rand
+    >>> preds = rand([16, 3, 16, 16])
+    >>> target = rand([16, 3, 16, 16])
     >>> sam = _SpectralAngleMapper()
     >>> sam(preds, target)
     tensor(0.5914)
@@ -169,10 +166,9 @@ def __init__(
 class _SpectralDistortionIndex(SpectralDistortionIndex):
     """Wrapper for deprecated import.
 
-    >>> import torch
-    >>> _ = torch.manual_seed(42)
-    >>> preds = torch.rand([16, 3, 16, 16])
-    >>> target = torch.rand([16, 3, 16, 16])
+    >>> from torch import rand
+    >>> preds = rand([16, 3, 16, 16])
+    >>> target = rand([16, 3, 16, 16])
     >>> sdi = _SpectralDistortionIndex()
     >>> sdi(preds, target)
     tensor(0.0234)
@@ -229,10 +225,9 @@ def __init__(
 class _TotalVariation(TotalVariation):
     """Wrapper for deprecated import.
 
-    >>> import torch
-    >>> _ = torch.manual_seed(42)
+    >>> from torch import rand
     >>> tv = _TotalVariation()
-    >>> img = torch.rand(5, 3, 28, 28)
+    >>> img = rand(5, 3, 28, 28)
     >>> tv(img)
     tensor(7546.8018)
 
diff --git a/src/torchmetrics/image/d_lambda.py b/src/torchmetrics/image/d_lambda.py
index ff232569748..5b1e58de0dd 100644
--- a/src/torchmetrics/image/d_lambda.py
+++ b/src/torchmetrics/image/d_lambda.py
@@ -53,11 +53,10 @@ class SpectralDistortionIndex(Metric):
         kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info.
 
     Example:
-        >>> import torch
-        >>> _ = torch.manual_seed(42)
+        >>> from torch import rand
         >>> from torchmetrics.image import SpectralDistortionIndex
-        >>> preds = torch.rand([16, 3, 16, 16])
-        >>> target = torch.rand([16, 3, 16, 16])
+        >>> preds = rand([16, 3, 16, 16])
+        >>> target = rand([16, 3, 16, 16])
         >>> sdi = SpectralDistortionIndex()
         >>> sdi(preds, target)
         tensor(0.0234)
@@ -126,11 +125,10 @@ def plot(
             :scale: 75
 
             >>> # Example plotting a single value
-            >>> import torch
-            >>> _ = torch.manual_seed(42)
+            >>> from torch import rand
             >>> from torchmetrics.image import SpectralDistortionIndex
-            >>> preds = torch.rand([16, 3, 16, 16])
-            >>> target = torch.rand([16, 3, 16, 16])
+            >>> preds = rand([16, 3, 16, 16])
+            >>> target = rand([16, 3, 16, 16])
             >>> metric = SpectralDistortionIndex()
             >>> metric.update(preds, target)
             >>> fig_, ax_ = metric.plot()
@@ -139,11 +137,10 @@ def plot(
             :scale: 75
 
             >>> # Example plotting multiple values
-            >>> import torch
-            >>> _ = torch.manual_seed(42)
+            >>> from torch import rand
             >>> from torchmetrics.image import SpectralDistortionIndex
-            >>> preds = torch.rand([16, 3, 16, 16])
-            >>> target = torch.rand([16, 3, 16, 16])
+            >>> preds = rand([16, 3, 16, 16])
+            >>> target = rand([16, 3, 16, 16])
             >>> metric = SpectralDistortionIndex()
             >>> values = [ ]
             >>> for _ in range(10):
diff --git a/src/torchmetrics/image/d_s.py b/src/torchmetrics/image/d_s.py
index 434561c558a..a8dacbaf447 100644
--- a/src/torchmetrics/image/d_s.py
+++ b/src/torchmetrics/image/d_s.py
@@ -74,13 +74,12 @@ class SpatialDistortionIndex(Metric):
         kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info.
 
     Example:
-        >>> import torch
-        >>> _ = torch.manual_seed(42)
+        >>> from torch import rand
         >>> from torchmetrics.image import SpatialDistortionIndex
-        >>> preds = torch.rand([16, 3, 32, 32])
+        >>> preds = rand([16, 3, 32, 32])
         >>> target = {
-        ...     'ms': torch.rand([16, 3, 16, 16]),
-        ...     'pan': torch.rand([16, 3, 32, 32]),
+        ...     'ms': rand([16, 3, 16, 16]),
+        ...     'pan': rand([16, 3, 32, 32]),
         ... }
         >>> sdi = SpatialDistortionIndex()
         >>> sdi(preds, target)
@@ -191,13 +190,12 @@ def plot(
             :scale: 75
 
             >>> # Example plotting a single value
-            >>> import torch
-            >>> _ = torch.manual_seed(42)
+            >>> from torch import rand
             >>> from torchmetrics.image import SpatialDistortionIndex
-            >>> preds = torch.rand([16, 3, 32, 32])
+            >>> preds = rand([16, 3, 32, 32])
             >>> target = {
-            ...     'ms': torch.rand([16, 3, 16, 16]),
-            ...     'pan': torch.rand([16, 3, 32, 32]),
+            ...     'ms': rand([16, 3, 16, 16]),
+            ...     'pan': rand([16, 3, 32, 32]),
             ... }
             >>> metric = SpatialDistortionIndex()
             >>> metric.update(preds, target)
@@ -207,13 +205,12 @@ def plot(
             :scale: 75
 
             >>> # Example plotting multiple values
-            >>> import torch
-            >>> _ = torch.manual_seed(42)
+            >>> from torch import rand
             >>> from torchmetrics.image import SpatialDistortionIndex
-            >>> preds = torch.rand([16, 3, 32, 32])
+            >>> preds = rand([16, 3, 32, 32])
             >>> target = {
-            ...     'ms': torch.rand([16, 3, 16, 16]),
-            ...     'pan': torch.rand([16, 3, 32, 32]),
+            ...     'ms': rand([16, 3, 16, 16]),
+            ...     'pan': rand([16, 3, 32, 32]),
             ... }
             >>> metric = SpatialDistortionIndex()
             >>> values = [ ]
diff --git a/src/torchmetrics/image/ergas.py b/src/torchmetrics/image/ergas.py
index f1d8da2073e..bf6b1c99a10 100644
--- a/src/torchmetrics/image/ergas.py
+++ b/src/torchmetrics/image/ergas.py
@@ -62,12 +62,12 @@ class ErrorRelativeGlobalDimensionlessSynthesis(Metric):
         kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info.
 
     Example:
-        >>> import torch
+        >>> from torch import rand
         >>> from torchmetrics.image import ErrorRelativeGlobalDimensionlessSynthesis
-        >>> preds = torch.rand([16, 1, 16, 16], generator=torch.manual_seed(42))
+        >>> preds = rand([16, 1, 16, 16])
         >>> target = preds * 0.75
         >>> ergas = ErrorRelativeGlobalDimensionlessSynthesis()
-        >>> torch.round(ergas(preds, target))
+        >>> ergas(preds, target).round()
         tensor(10.)
 
     """
@@ -131,9 +131,9 @@ def plot(
             :scale: 75
 
             >>> # Example plotting a single value
-            >>> import torch
+            >>> from torch import rand
             >>> from torchmetrics.image import ErrorRelativeGlobalDimensionlessSynthesis
-            >>> preds = torch.rand([16, 1, 16, 16], generator=torch.manual_seed(42))
+            >>> preds = rand([16, 1, 16, 16])
             >>> target = preds * 0.75
             >>> metric = ErrorRelativeGlobalDimensionlessSynthesis()
             >>> metric.update(preds, target)
@@ -143,9 +143,9 @@ def plot(
             :scale: 75
 
             >>> # Example plotting multiple values
-            >>> import torch
+            >>> from torch import rand
             >>> from torchmetrics.image import ErrorRelativeGlobalDimensionlessSynthesis
-            >>> preds = torch.rand([16, 1, 16, 16], generator=torch.manual_seed(42))
+            >>> preds = rand([16, 1, 16, 16])
             >>> target = preds * 0.75
             >>> metric = ErrorRelativeGlobalDimensionlessSynthesis()
             >>> values = [ ]
diff --git a/src/torchmetrics/image/fid.py b/src/torchmetrics/image/fid.py
index af4b93d7ad5..8c2e5d3cf76 100644
--- a/src/torchmetrics/image/fid.py
+++ b/src/torchmetrics/image/fid.py
@@ -265,8 +265,7 @@ class FrechetInceptionDistance(Metric):
             If ``reset_real_features`` is not an ``bool``
 
     Example:
-        >>> import torch
-        >>> _ = torch.manual_seed(123)
+        >>> from torch import rand
         >>> from torchmetrics.image.fid import FrechetInceptionDistance
         >>> fid = FrechetInceptionDistance(feature=64)
         >>> # generate two slightly overlapping image intensity distributions
@@ -275,7 +274,7 @@ class FrechetInceptionDistance(Metric):
         >>> fid.update(imgs_dist1, real=True)
         >>> fid.update(imgs_dist2, real=False)
         >>> fid.compute()
-        tensor(12.7202)
+        tensor(12.6388)
 
     """
 
diff --git a/src/torchmetrics/image/inception.py b/src/torchmetrics/image/inception.py
index 4913a5fe50b..2b125542a17 100644
--- a/src/torchmetrics/image/inception.py
+++ b/src/torchmetrics/image/inception.py
@@ -84,15 +84,14 @@ class InceptionScore(Metric):
             If ``feature`` is not an ``str``, ``int`` or ``torch.nn.Module``
 
     Example:
-        >>> import torch
-        >>> _ = torch.manual_seed(123)
+        >>> from torch import rand
         >>> from torchmetrics.image.inception import InceptionScore
         >>> inception = InceptionScore()
         >>> # generate some images
         >>> imgs = torch.randint(0, 255, (100, 3, 299, 299), dtype=torch.uint8)
         >>> inception.update(imgs)
         >>> inception.compute()
-        (tensor(1.0544), tensor(0.0117))
+        (tensor(1.0549), tensor(0.0121))
 
     """
 
diff --git a/src/torchmetrics/image/kid.py b/src/torchmetrics/image/kid.py
index e080116a33f..975edf800eb 100644
--- a/src/torchmetrics/image/kid.py
+++ b/src/torchmetrics/image/kid.py
@@ -148,17 +148,16 @@ class KernelInceptionDistance(Metric):
             If ``reset_real_features`` is not an ``bool``
 
     Example:
-        >>> import torch
-        >>> _ = torch.manual_seed(123)
+        >>> from torch import randint
         >>> from torchmetrics.image.kid import KernelInceptionDistance
         >>> kid = KernelInceptionDistance(subset_size=50)
         >>> # generate two slightly overlapping image intensity distributions
-        >>> imgs_dist1 = torch.randint(0, 200, (100, 3, 299, 299), dtype=torch.uint8)
-        >>> imgs_dist2 = torch.randint(100, 255, (100, 3, 299, 299), dtype=torch.uint8)
+        >>> imgs_dist1 = randint(0, 200, (100, 3, 299, 299), dtype=torch.uint8)
+        >>> imgs_dist2 = randint(100, 255, (100, 3, 299, 299), dtype=torch.uint8)
         >>> kid.update(imgs_dist1, real=True)
         >>> kid.update(imgs_dist2, real=False)
         >>> kid.compute()
-        (tensor(0.0337), tensor(0.0023))
+        (tensor(0.0312), tensor(0.0025))
 
     """
 
diff --git a/src/torchmetrics/image/lpip.py b/src/torchmetrics/image/lpip.py
index c094003fa4f..f1adb73648a 100644
--- a/src/torchmetrics/image/lpip.py
+++ b/src/torchmetrics/image/lpip.py
@@ -78,15 +78,14 @@ class LearnedPerceptualImagePatchSimilarity(Metric):
             If ``reduction`` is not one of ``"mean"`` or ``"sum"``
 
     Example:
-        >>> import torch
-        >>> _ = torch.manual_seed(123)
+        >>> from torch import rand
         >>> from torchmetrics.image.lpip import LearnedPerceptualImagePatchSimilarity
         >>> lpips = LearnedPerceptualImagePatchSimilarity(net_type='squeeze')
         >>> # LPIPS needs the images to be in the [-1, 1] range.
-        >>> img1 = (torch.rand(10, 3, 100, 100) * 2) - 1
-        >>> img2 = (torch.rand(10, 3, 100, 100) * 2) - 1
+        >>> img1 = (rand(10, 3, 100, 100) * 2) - 1
+        >>> img2 = (rand(10, 3, 100, 100) * 2) - 1
         >>> lpips(img1, img2)
-        tensor(0.1046)
+        tensor(0.1024)
 
     """
 
diff --git a/src/torchmetrics/image/mifid.py b/src/torchmetrics/image/mifid.py
index 8c1084e6458..7d7237b7416 100644
--- a/src/torchmetrics/image/mifid.py
+++ b/src/torchmetrics/image/mifid.py
@@ -129,13 +129,12 @@ class MemorizationInformedFrechetInceptionDistance(Metric):
             If ``reset_real_features`` is not an ``bool``
 
     Example::
-        >>> import torch
-        >>> _ = torch.manual_seed(42)
+        >>> from torch import randint
         >>> from torchmetrics.image.mifid import MemorizationInformedFrechetInceptionDistance
         >>> mifid = MemorizationInformedFrechetInceptionDistance(feature=64)
         >>> # generate two slightly overlapping image intensity distributions
-        >>> imgs_dist1 = torch.randint(0, 200, (100, 3, 299, 299), dtype=torch.uint8)
-        >>> imgs_dist2 = torch.randint(100, 255, (100, 3, 299, 299), dtype=torch.uint8)
+        >>> imgs_dist1 = randint(0, 200, (100, 3, 299, 299), dtype=torch.uint8)
+        >>> imgs_dist2 = randint(100, 255, (100, 3, 299, 299), dtype=torch.uint8)
         >>> mifid.update(imgs_dist1, real=True)
         >>> mifid.update(imgs_dist2, real=False)
         >>> mifid.compute()
diff --git a/src/torchmetrics/image/perceptual_path_length.py b/src/torchmetrics/image/perceptual_path_length.py
index 6b89b36b1c1..4e8cca23343 100644
--- a/src/torchmetrics/image/perceptual_path_length.py
+++ b/src/torchmetrics/image/perceptual_path_length.py
@@ -98,9 +98,8 @@ class PerceptualPathLength(Metric):
             If ``upper_discard`` is not a float between 0 and 1 or None.
 
     Example::
-        >>> from torchmetrics.image import PerceptualPathLength
         >>> import torch
-        >>> _ = torch.manual_seed(42)
+        >>> from torchmetrics.image import PerceptualPathLength
         >>> class DummyGenerator(torch.nn.Module):
         ...    def __init__(self, z_size) -> None:
         ...       super().__init__()
@@ -112,10 +111,10 @@ class PerceptualPathLength(Metric):
         ...      return torch.randn(num_samples, self.z_size)
         >>> generator = DummyGenerator(2)
         >>> ppl = PerceptualPathLength(num_samples=10)
-        >>> ppl(generator)  # doctest: +SKIP
-        (tensor(0.2371),
-        tensor(0.1763),
-        tensor([0.3502, 0.1362, 0.2535, 0.0902, 0.1784, 0.0769, 0.5871, 0.0691, 0.3921]))
+        >>> ppl(generator)
+        (tensor(0.2369),
+         tensor(0.1760),
+         tensor([0.3489, 0.1363, 0.2535, 0.0907, 0.1785, 0.0769, 0.5864, 0.0691, 0.3920]))
 
     """
 
diff --git a/src/torchmetrics/image/psnrb.py b/src/torchmetrics/image/psnrb.py
index dc050e81fb8..bac58b84e46 100644
--- a/src/torchmetrics/image/psnrb.py
+++ b/src/torchmetrics/image/psnrb.py
@@ -51,12 +51,10 @@ class PeakSignalNoiseRatioWithBlockedEffect(Metric):
         kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info.
 
     Example:
-        >>> import torch
-        >>> from torchmetrics.image import PeakSignalNoiseRatioWithBlockedEffect
+        >>> from torch import rand
         >>> metric = PeakSignalNoiseRatioWithBlockedEffect()
-        >>> _ = torch.manual_seed(42)
-        >>> preds = torch.rand(2, 1, 10, 10)
-        >>> target = torch.rand(2, 1, 10, 10)
+        >>> preds = rand(2, 1, 10, 10)
+        >>> target = rand(2, 1, 10, 10)
         >>> metric(preds, target)
         tensor(7.2893)
 
diff --git a/src/torchmetrics/image/qnr.py b/src/torchmetrics/image/qnr.py
index 96023db8aab..b226a6b19fd 100644
--- a/src/torchmetrics/image/qnr.py
+++ b/src/torchmetrics/image/qnr.py
@@ -70,13 +70,12 @@ class QualityWithNoReference(Metric):
         kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info.
 
     Example:
-        >>> import torch
-        >>> _ = torch.manual_seed(42)
+        >>> from torch import rand
         >>> from torchmetrics.image import QualityWithNoReference
-        >>> preds = torch.rand([16, 3, 32, 32])
+        >>> preds = rand([16, 3, 32, 32])
         >>> target = {
-        ...     'ms': torch.rand([16, 3, 16, 16]),
-        ...     'pan': torch.rand([16, 3, 32, 32]),
+        ...     'ms': rand([16, 3, 16, 16]),
+        ...     'pan': rand([16, 3, 32, 32]),
         ... }
         >>> qnr = QualityWithNoReference()
         >>> qnr(preds, target)
@@ -195,13 +194,12 @@ def plot(
             :scale: 75
 
             >>> # Example plotting a single value
-            >>> import torch
-            >>> _ = torch.manual_seed(42)
+            >>> from torch import rand
             >>> from torchmetrics.image import QualityWithNoReference
-            >>> preds = torch.rand([16, 3, 32, 32])
+            >>> preds = rand([16, 3, 32, 32])
             >>> target = {
-            ...     'ms': torch.rand([16, 3, 16, 16]),
-            ...     'pan': torch.rand([16, 3, 32, 32]),
+            ...     'ms': rand([16, 3, 16, 16]),
+            ...     'pan': rand([16, 3, 32, 32]),
             ... }
             >>> metric = QualityWithNoReference()
             >>> metric.update(preds, target)
@@ -211,13 +209,12 @@ def plot(
             :scale: 75
 
             >>> # Example plotting multiple values
-            >>> import torch
-            >>> _ = torch.manual_seed(42)
+            >>> from torch import rand
             >>> from torchmetrics.image import QualityWithNoReference
-            >>> preds = torch.rand([16, 3, 32, 32])
+            >>> preds = rand([16, 3, 32, 32])
             >>> target = {
-            ...     'ms': torch.rand([16, 3, 16, 16]),
-            ...     'pan': torch.rand([16, 3, 32, 32]),
+            ...     'ms': rand([16, 3, 16, 16]),
+            ...     'pan': rand([16, 3, 32, 32]),
             ... }
             >>> metric = QualityWithNoReference()
             >>> values = [ ]
diff --git a/src/torchmetrics/image/rase.py b/src/torchmetrics/image/rase.py
index c422762eb68..b1eb32141a6 100644
--- a/src/torchmetrics/image/rase.py
+++ b/src/torchmetrics/image/rase.py
@@ -46,14 +46,12 @@ class RelativeAverageSpectralError(Metric):
         Relative Average Spectral Error (RASE)
 
     Example:
-        >>> import torch
-        >>> from torchmetrics.image import RelativeAverageSpectralError
-        >>> g = torch.manual_seed(22)
-        >>> preds = torch.rand(4, 3, 16, 16)
-        >>> target = torch.rand(4, 3, 16, 16)
+        >>> from torch import rand
+        >>> preds = rand(4, 3, 16, 16)
+        >>> target = rand(4, 3, 16, 16)
         >>> rase = RelativeAverageSpectralError()
         >>> rase(preds, target)
-        tensor(5114.66...)
+        tensor(5326.40...)
 
     Raises:
         ValueError: If ``window_size`` is not a positive integer.
@@ -124,13 +122,12 @@ def plot(
             :scale: 75
 
             >>> # Example plotting multiple values
-            >>> import torch
-            >>> _ = torch.manual_seed(42)
+            >>> from torch import rand
             >>> from torchmetrics.image import RelativeAverageSpectralError
             >>> metric = RelativeAverageSpectralError()
             >>> values = [ ]
             >>> for _ in range(10):
-            ...     values.append(metric(torch.rand(4, 3, 16, 16), torch.rand(4, 3, 16, 16)))
+            ...     values.append(metric(rand(4, 3, 16, 16), rand(4, 3, 16, 16)))
             >>> fig_, ax_ = metric.plot(values)
 
         """
diff --git a/src/torchmetrics/image/rmse_sw.py b/src/torchmetrics/image/rmse_sw.py
index e0838ec760d..c1f7c652879 100644
--- a/src/torchmetrics/image/rmse_sw.py
+++ b/src/torchmetrics/image/rmse_sw.py
@@ -43,13 +43,13 @@ class RootMeanSquaredErrorUsingSlidingWindow(Metric):
         kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info.
 
     Example:
+        >>> from torch import rand
         >>> from torchmetrics.image import RootMeanSquaredErrorUsingSlidingWindow
-        >>> g = torch.manual_seed(22)
-        >>> preds = torch.rand(4, 3, 16, 16)
-        >>> target = torch.rand(4, 3, 16, 16)
+        >>> preds = rand(4, 3, 16, 16)
+        >>> target = rand(4, 3, 16, 16)
         >>> rmse_sw = RootMeanSquaredErrorUsingSlidingWindow()
         >>> rmse_sw(preds, target)
-        tensor(0.3999)
+        tensor(0.4158)
 
     Raises:
         ValueError: If ``window_size`` is not a positive integer.
diff --git a/src/torchmetrics/image/sam.py b/src/torchmetrics/image/sam.py
index 47d4839c5e2..7aad1782852 100644
--- a/src/torchmetrics/image/sam.py
+++ b/src/torchmetrics/image/sam.py
@@ -56,11 +56,10 @@ class SpectralAngleMapper(Metric):
         Tensor with SpectralAngleMapper score
 
     Example:
-        >>> import torch
+        >>> from torch import rand
         >>> from torchmetrics.image import SpectralAngleMapper
-        >>> gen = torch.manual_seed(42)
-        >>> preds = torch.rand([16, 3, 16, 16], generator=gen)
-        >>> target = torch.rand([16, 3, 16, 16], generator=gen)
+        >>> preds = rand([16, 3, 16, 16])
+        >>> target = rand([16, 3, 16, 16])
         >>> sam = SpectralAngleMapper()
         >>> sam(preds, target)
         tensor(0.5914)
@@ -141,11 +140,10 @@ def plot(
             :scale: 75
 
             >>> # Example plotting single value
-            >>> import torch
+            >>> from torch import rand
             >>> from torchmetrics.image import SpectralAngleMapper
-            >>> gen = torch.manual_seed(42)
-            >>> preds = torch.rand([16, 3, 16, 16], generator=gen)
-            >>> target = torch.rand([16, 3, 16, 16], generator=gen)
+            >>> preds = rand([16, 3, 16, 16])
+            >>> target = rand([16, 3, 16, 16])
             >>> metric = SpectralAngleMapper()
             >>> metric.update(preds, target)
             >>> fig_, ax_ = metric.plot()
@@ -154,11 +152,10 @@ def plot(
             :scale: 75
 
             >>> # Example plotting multiple values
-            >>> import torch
+            >>> from torch import rand
             >>> from torchmetrics.image import SpectralAngleMapper
-            >>> gen = torch.manual_seed(42)
-            >>> preds = torch.rand([16, 3, 16, 16], generator=gen)
-            >>> target = torch.rand([16, 3, 16, 16], generator=gen)
+            >>> preds = rand([16, 3, 16, 16])
+            >>> target = rand([16, 3, 16, 16])
             >>> metric = SpectralAngleMapper()
             >>> values = [ ]
             >>> for _ in range(10):
diff --git a/src/torchmetrics/image/scc.py b/src/torchmetrics/image/scc.py
index 15ea2b96ecf..fac28658f63 100644
--- a/src/torchmetrics/image/scc.py
+++ b/src/torchmetrics/image/scc.py
@@ -39,11 +39,10 @@ class SpatialCorrelationCoefficient(Metric):
         kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info.
 
     Example:
-        >>> import torch
-        >>> _ = torch.manual_seed(42)
+        >>> from torch import randn
         >>> from torchmetrics.image import SpatialCorrelationCoefficient as SCC
-        >>> preds = torch.randn([32, 3, 64, 64])
-        >>> target = torch.randn([32, 3, 64, 64])
+        >>> preds = randn([32, 3, 64, 64])
+        >>> target = randn([32, 3, 64, 64])
         >>> scc = SCC()
         >>> scc(preds, target)
         tensor(0.0023)
diff --git a/src/torchmetrics/image/ssim.py b/src/torchmetrics/image/ssim.py
index 5056589fd14..f0c03a163d6 100644
--- a/src/torchmetrics/image/ssim.py
+++ b/src/torchmetrics/image/ssim.py
@@ -268,10 +268,9 @@ class MultiScaleStructuralSimilarityIndexMeasure(Metric):
             If ``normalize`` is neither `None`, `ReLU` nor `simple`.
 
     Example:
+        >>> from torch import rand
         >>> from torchmetrics.image import MultiScaleStructuralSimilarityIndexMeasure
-        >>> import torch
-        >>> gen = torch.manual_seed(42)
-        >>> preds = torch.rand([3, 3, 256, 256], generator=torch.manual_seed(42))
+        >>> preds = torch.rand([3, 3, 256, 256])
         >>> target = preds * 0.75
         >>> ms_ssim = MultiScaleStructuralSimilarityIndexMeasure(data_range=1.0)
         >>> ms_ssim(preds, target)
@@ -394,9 +393,9 @@ def plot(
             :scale: 75
 
             >>> # Example plotting a single value
+            >>> from torch import rand
             >>> from torchmetrics.image import MultiScaleStructuralSimilarityIndexMeasure
-            >>> import torch
-            >>> preds = torch.rand([3, 3, 256, 256], generator=torch.manual_seed(42))
+            >>> preds = rand([3, 3, 256, 256])
             >>> target = preds * 0.75
             >>> metric = MultiScaleStructuralSimilarityIndexMeasure(data_range=1.0)
             >>> metric.update(preds, target)
@@ -406,9 +405,9 @@ def plot(
             :scale: 75
 
             >>> # Example plotting multiple values
+            >>> from torch import rand
             >>> from torchmetrics.image import MultiScaleStructuralSimilarityIndexMeasure
-            >>> import torch
-            >>> preds = torch.rand([3, 3, 256, 256], generator=torch.manual_seed(42))
+            >>> preds = rand([3, 3, 256, 256])
             >>> target = preds * 0.75
             >>> metric = MultiScaleStructuralSimilarityIndexMeasure(data_range=1.0)
             >>> values = [ ]
diff --git a/src/torchmetrics/image/tv.py b/src/torchmetrics/image/tv.py
index 972a07b745d..ca6276b7e86 100644
--- a/src/torchmetrics/image/tv.py
+++ b/src/torchmetrics/image/tv.py
@@ -53,9 +53,8 @@ class TotalVariation(Metric):
             If ``reduction`` is not one of ``'sum'``, ``'mean'``, ``'none'`` or ``None``
 
     Example:
-        >>> import torch
+        >>> from torch import rand
         >>> from torchmetrics.image import TotalVariation
-        >>> _ = torch.manual_seed(42)
         >>> tv = TotalVariation()
         >>> img = torch.rand(5, 3, 28, 28)
         >>> tv(img)
diff --git a/src/torchmetrics/image/vif.py b/src/torchmetrics/image/vif.py
index 3e844932399..0358cb80e66 100644
--- a/src/torchmetrics/image/vif.py
+++ b/src/torchmetrics/image/vif.py
@@ -37,11 +37,10 @@ class VisualInformationFidelity(Metric):
         kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info.
 
     Example:
-        >>> import torch
-        >>> _ = torch.manual_seed(42)
+        >>> from torch import randn
         >>> from torchmetrics.image import VisualInformationFidelity
-        >>> preds = torch.randn([32, 3, 41, 41])
-        >>> target = torch.randn([32, 3, 41, 41])
+        >>> preds = randn([32, 3, 41, 41])
+        >>> target = randn([32, 3, 41, 41])
         >>> vif = VisualInformationFidelity()
         >>> vif(preds, target)
         tensor(0.0032)
diff --git a/src/torchmetrics/multimodal/clip_iqa.py b/src/torchmetrics/multimodal/clip_iqa.py
index b3f934fee33..6ab75356047 100644
--- a/src/torchmetrics/multimodal/clip_iqa.py
+++ b/src/torchmetrics/multimodal/clip_iqa.py
@@ -128,10 +128,9 @@ class CLIPImageQualityAssessment(Metric):
     Example::
         Single prompt:
 
+        >>> from torch import randint
         >>> from torchmetrics.multimodal import CLIPImageQualityAssessment
-        >>> import torch
-        >>> _ = torch.manual_seed(42)
-        >>> imgs = torch.randint(255, (2, 3, 224, 224)).float()
+        >>> imgs = randint(255, (2, 3, 224, 224)).float()
         >>> metric = CLIPImageQualityAssessment()
         >>> metric(imgs)
         tensor([0.8894, 0.8902])
@@ -139,10 +138,9 @@ class CLIPImageQualityAssessment(Metric):
     Example::
         Multiple prompts:
 
+        >>> from torch import randint
         >>> from torchmetrics.multimodal import CLIPImageQualityAssessment
-        >>> import torch
-        >>> _ = torch.manual_seed(42)
-        >>> imgs = torch.randint(255, (2, 3, 224, 224)).float()
+        >>> imgs = randint(255, (2, 3, 224, 224)).float()
         >>> metric = CLIPImageQualityAssessment(prompts=("quality", "brightness"))
         >>> metric(imgs)
         {'quality': tensor([0.8894, 0.8902]), 'brightness': tensor([0.5507, 0.5208])}
@@ -150,10 +148,9 @@ class CLIPImageQualityAssessment(Metric):
     Example::
         Custom prompts. Must always be a tuple of length 2, with a positive and negative prompt.
 
+        >>> from torch import randint
         >>> from torchmetrics.multimodal import CLIPImageQualityAssessment
-        >>> import torch
-        >>> _ = torch.manual_seed(42)
-        >>> imgs = torch.randint(255, (2, 3, 224, 224)).float()
+        >>> imgs = randint(255, (2, 3, 224, 224)).float()
         >>> metric = CLIPImageQualityAssessment(prompts=(("Super good photo.", "Super bad photo."), "brightness"))
         >>> metric(imgs)
         {'user_defined_0': tensor([0.9652, 0.9629]), 'brightness': tensor([0.5507, 0.5208])}
diff --git a/src/torchmetrics/multimodal/clip_score.py b/src/torchmetrics/multimodal/clip_score.py
index eb432e0be16..47bcbe3b47f 100644
--- a/src/torchmetrics/multimodal/clip_score.py
+++ b/src/torchmetrics/multimodal/clip_score.py
@@ -82,10 +82,10 @@ class CLIPScore(Metric):
             If transformers package is not installed or version is lower than 4.10.0
 
     Example:
-        >>> import torch
+        >>> from torch import randint
         >>> from torchmetrics.multimodal.clip_score import CLIPScore
         >>> metric = CLIPScore(model_name_or_path="openai/clip-vit-base-patch16")
-        >>> score = metric(torch.randint(255, (3, 224, 224), generator=torch.manual_seed(42)), "a photo of a cat")
+        >>> score = metric(randint(255, (3, 224, 224)), "a photo of a cat")
         >>> score.detach()
         tensor(24.4255)
 
diff --git a/src/torchmetrics/nominal/cramers.py b/src/torchmetrics/nominal/cramers.py
index 2d780e7e379..df47cc079d1 100644
--- a/src/torchmetrics/nominal/cramers.py
+++ b/src/torchmetrics/nominal/cramers.py
@@ -69,10 +69,10 @@ class CramersV(Metric):
 
     Example::
 
+        >>> from torch import randint, randn
         >>> from torchmetrics.nominal import CramersV
-        >>> _ = torch.manual_seed(42)
-        >>> preds = torch.randint(0, 4, (100,))
-        >>> target = torch.round(preds + torch.randn(100)).clamp(0, 4)
+        >>> preds = randint(0, 4, (100,))
+        >>> target = (preds + randn(100)).round().clamp(0, 4)
         >>> cramers_v = CramersV(num_classes=5)
         >>> cramers_v(preds, target)
         tensor(0.5284)
diff --git a/src/torchmetrics/nominal/fleiss_kappa.py b/src/torchmetrics/nominal/fleiss_kappa.py
index 9518302cdac..619e8196d4c 100644
--- a/src/torchmetrics/nominal/fleiss_kappa.py
+++ b/src/torchmetrics/nominal/fleiss_kappa.py
@@ -54,23 +54,21 @@ class FleissKappa(Metric):
 
     Example:
         >>> # Ratings are provided as counts
-        >>> import torch
+        >>> from torch import randint
         >>> from torchmetrics.nominal import FleissKappa
-        >>> _ = torch.manual_seed(42)
-        >>> ratings = torch.randint(0, 10, size=(100, 5)).long()  # 100 samples, 5 categories, 10 raters
+        >>> ratings = randint(0, 10, size=(100, 5)).long()  # 100 samples, 5 categories, 10 raters
         >>> metric = FleissKappa(mode='counts')
         >>> metric(ratings)
         tensor(0.0089)
 
     Example:
         >>> # Ratings are provided as probabilities
-        >>> import torch
+        >>> from torch import randn
         >>> from torchmetrics.nominal import FleissKappa
-        >>> _ = torch.manual_seed(42)
-        >>> ratings = torch.randn(100, 5, 10).softmax(dim=1)  # 100 samples, 5 categories, 10 raters
+        >>> ratings = randn(100, 5, 10).softmax(dim=1)  # 100 samples, 5 categories, 10 raters
         >>> metric = FleissKappa(mode='probs')
         >>> metric(ratings)
-        tensor(-0.0105)
+        tensor(-0.0075)
 
     """
 
diff --git a/src/torchmetrics/nominal/pearson.py b/src/torchmetrics/nominal/pearson.py
index 2fc88c8e851..a43cd548792 100644
--- a/src/torchmetrics/nominal/pearson.py
+++ b/src/torchmetrics/nominal/pearson.py
@@ -73,10 +73,10 @@ class PearsonsContingencyCoefficient(Metric):
 
     Example::
 
+        >>> from torch import randint, randn
         >>> from torchmetrics.nominal import PearsonsContingencyCoefficient
-        >>> _ = torch.manual_seed(42)
-        >>> preds = torch.randint(0, 4, (100,))
-        >>> target = torch.round(preds + torch.randn(100)).clamp(0, 4)
+        >>> preds = randint(0, 4, (100,))
+        >>> target = (preds + randn(100)).round().clamp(0, 4)
         >>> pearsons_contingency_coefficient = PearsonsContingencyCoefficient(num_classes=5)
         >>> pearsons_contingency_coefficient(preds, target)
         tensor(0.6948)
diff --git a/src/torchmetrics/nominal/theils_u.py b/src/torchmetrics/nominal/theils_u.py
index f82c7658b1f..7f7f22ecb1b 100644
--- a/src/torchmetrics/nominal/theils_u.py
+++ b/src/torchmetrics/nominal/theils_u.py
@@ -59,10 +59,10 @@ class TheilsU(Metric):
 
     Example::
 
+        >>> from torch import randint
         >>> from torchmetrics.nominal import TheilsU
-        >>> _ = torch.manual_seed(42)
-        >>> preds = torch.randint(10, (10,))
-        >>> target = torch.randint(10, (10,))
+        >>> preds = randint(10, (10,))
+        >>> target = randint(10, (10,))
         >>> metric = TheilsU(num_classes=10)
         >>> metric(preds, target)
         tensor(0.8530)
diff --git a/src/torchmetrics/nominal/tschuprows.py b/src/torchmetrics/nominal/tschuprows.py
index a14832b4121..9986fa2ec6f 100644
--- a/src/torchmetrics/nominal/tschuprows.py
+++ b/src/torchmetrics/nominal/tschuprows.py
@@ -69,10 +69,10 @@ class TschuprowsT(Metric):
 
     Example::
 
+        >>> from torch import randint
         >>> from torchmetrics.nominal import TschuprowsT
-        >>> _ = torch.manual_seed(42)
-        >>> preds = torch.randint(0, 4, (100,))
-        >>> target = torch.round(preds + torch.randn(100)).clamp(0, 4)
+        >>> preds = randint(0, 4, (100,))
+        >>> target = (preds + torch.randn(100)).round().clamp(0, 4)
         >>> tschuprows_t = TschuprowsT(num_classes=5)
         >>> tschuprows_t(preds, target)
         tensor(0.4930)
diff --git a/src/torchmetrics/regression/wmape.py b/src/torchmetrics/regression/wmape.py
index 067c995bfb2..42fadb906ef 100644
--- a/src/torchmetrics/regression/wmape.py
+++ b/src/torchmetrics/regression/wmape.py
@@ -51,10 +51,9 @@ class WeightedMeanAbsolutePercentageError(Metric):
         kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info.
 
     Example:
-        >>> import torch
-        >>> _ = torch.manual_seed(42)
-        >>> preds = torch.randn(20,)
-        >>> target = torch.randn(20,)
+        >>> from torch import randn
+        >>> preds = randn(20,)
+        >>> target = randn(20,)
         >>> wmape = WeightedMeanAbsolutePercentageError()
         >>> wmape(preds, target)
         tensor(1.3967)
diff --git a/src/torchmetrics/segmentation/generalized_dice.py b/src/torchmetrics/segmentation/generalized_dice.py
index 66f09437000..95da9ab26d9 100644
--- a/src/torchmetrics/segmentation/generalized_dice.py
+++ b/src/torchmetrics/segmentation/generalized_dice.py
@@ -89,20 +89,19 @@ class GeneralizedDiceScore(Metric):
             If ``input_format`` is not one of ``"one-hot"`` or ``"index"``
 
     Example:
-        >>> import torch
-        >>> _ = torch.manual_seed(0)
+        >>> from torch import randint
         >>> from torchmetrics.segmentation import GeneralizedDiceScore
         >>> gds = GeneralizedDiceScore(num_classes=3)
-        >>> preds = torch.randint(0, 2, (10, 3, 128, 128))
-        >>> target = torch.randint(0, 2, (10, 3, 128, 128))
+        >>> preds = randint(0, 2, (10, 3, 128, 128))
+        >>> target = randint(0, 2, (10, 3, 128, 128))
         >>> gds(preds, target)
-        tensor(0.4983)
+        tensor(0.4992)
         >>> gds = GeneralizedDiceScore(num_classes=3, per_class=True)
         >>> gds(preds, target)
-        tensor([0.4987, 0.4966, 0.4995])
+        tensor([0.5001, 0.4993, 0.4982])
         >>> gds = GeneralizedDiceScore(num_classes=3, per_class=True, include_background=False)
         >>> gds(preds, target)
-        tensor([0.4966, 0.4995])
+        tensor([0.4993, 0.4982])
 
     """
 
diff --git a/src/torchmetrics/segmentation/mean_iou.py b/src/torchmetrics/segmentation/mean_iou.py
index 77d465ebd21..c298254585a 100644
--- a/src/torchmetrics/segmentation/mean_iou.py
+++ b/src/torchmetrics/segmentation/mean_iou.py
@@ -70,20 +70,19 @@ class MeanIoU(Metric):
             If ``input_format`` is not one of ``"one-hot"`` or ``"index"``
 
     Example:
-        >>> import torch
-        >>> _ = torch.manual_seed(0)
+        >>> from torch import randint
         >>> from torchmetrics.segmentation import MeanIoU
         >>> miou = MeanIoU(num_classes=3)
-        >>> preds = torch.randint(0, 2, (10, 3, 128, 128))
-        >>> target = torch.randint(0, 2, (10, 3, 128, 128))
+        >>> preds = randint(0, 2, (10, 3, 128, 128))
+        >>> target = randint(0, 2, (10, 3, 128, 128))
         >>> miou(preds, target)
-        tensor(0.3318)
+        tensor(0.3326)
         >>> miou = MeanIoU(num_classes=3, per_class=True)
         >>> miou(preds, target)
-        tensor([0.3322, 0.3303, 0.3329])
+        tensor([0.3334, 0.3327, 0.3318])
         >>> miou = MeanIoU(num_classes=3, per_class=True, include_background=False)
         >>> miou(preds, target)
-        tensor([0.3303, 0.3329])
+        tensor([0.3327, 0.3318])
 
     """
 
diff --git a/src/torchmetrics/text/_deprecated.py b/src/torchmetrics/text/_deprecated.py
index d3ba1c4010e..0c7ffef29af 100644
--- a/src/torchmetrics/text/_deprecated.py
+++ b/src/torchmetrics/text/_deprecated.py
@@ -144,10 +144,9 @@ def __init__(
 class _Perplexity(Perplexity):
     """Wrapper for deprecated import.
 
-    >>> import torch
-    >>> gen = torch.manual_seed(42)
-    >>> preds = torch.rand(2, 8, 5, generator=gen)
-    >>> target = torch.randint(5, (2, 8), generator=gen)
+    >>> from torch import rand, randint
+    >>> preds = rand(2, 8, 5)
+    >>> target = randint(5, (2, 8))
     >>> target[0, 6:] = -100
     >>> perp = _Perplexity(ignore_index=-100)
     >>> perp(preds, target)
diff --git a/src/torchmetrics/text/perplexity.py b/src/torchmetrics/text/perplexity.py
index 51804881df8..d13eac2f402 100644
--- a/src/torchmetrics/text/perplexity.py
+++ b/src/torchmetrics/text/perplexity.py
@@ -48,11 +48,10 @@ class Perplexity(Metric):
             Additional keyword arguments, see :ref:`Metric kwargs` for more info.
 
     Examples:
+        >>> from torch import rand, randint
         >>> from torchmetrics.text import Perplexity
-        >>> import torch
-        >>> gen = torch.manual_seed(42)
-        >>> preds = torch.rand(2, 8, 5, generator=gen)
-        >>> target = torch.randint(5, (2, 8), generator=gen)
+        >>> preds = rand(2, 8, 5)
+        >>> target = randint(5, (2, 8))
         >>> target[0, 6:] = -100
         >>> perp = Perplexity(ignore_index=-100)
         >>> perp(preds, target)
diff --git a/src/torchmetrics/wrappers/bootstrapping.py b/src/torchmetrics/wrappers/bootstrapping.py
index 9b904568b65..d59f7724c2a 100644
--- a/src/torchmetrics/wrappers/bootstrapping.py
+++ b/src/torchmetrics/wrappers/bootstrapping.py
@@ -75,15 +75,15 @@ class basically keeps multiple copies of the same base metric in memory and when
 
     Example::
         >>> from pprint import pprint
+        >>> from torch import randint
         >>> from torchmetrics.wrappers import BootStrapper
         >>> from torchmetrics.classification import MulticlassAccuracy
-        >>> _ = torch.manual_seed(123)
         >>> base_metric = MulticlassAccuracy(num_classes=5, average='micro')
         >>> bootstrap = BootStrapper(base_metric, num_bootstraps=20)
-        >>> bootstrap.update(torch.randint(5, (20,)), torch.randint(5, (20,)))
+        >>> bootstrap.update(randint(5, (20,)), randint(5, (20,)))
         >>> output = bootstrap.compute()
         >>> pprint(output)
-        {'mean': tensor(0.2205), 'std': tensor(0.0859)}
+        {'mean': tensor(0.2089), 'std': tensor(0.0772)}
 
     """
 
diff --git a/src/torchmetrics/wrappers/classwise.py b/src/torchmetrics/wrappers/classwise.py
index 78cb27ae46c..217c94d6bc0 100644
--- a/src/torchmetrics/wrappers/classwise.py
+++ b/src/torchmetrics/wrappers/classwise.py
@@ -44,58 +44,54 @@ class ClasswiseWrapper(WrapperMetric):
     Example::
         Basic example where the output of a metric is unwrapped into a dictionary with the class index as keys:
 
-        >>> import torch
-        >>> _ = torch.manual_seed(42)
+        >>> from torch import randint, randn
         >>> from torchmetrics.wrappers import ClasswiseWrapper
         >>> from torchmetrics.classification import MulticlassAccuracy
         >>> metric = ClasswiseWrapper(MulticlassAccuracy(num_classes=3, average=None))
-        >>> preds = torch.randn(10, 3).softmax(dim=-1)
-        >>> target = torch.randint(3, (10,))
+        >>> preds = randn(10, 3).softmax(dim=-1)
+        >>> target = randint(3, (10,))
         >>> metric(preds, target)  # doctest: +NORMALIZE_WHITESPACE
         {'multiclassaccuracy_0': tensor(0.5000),
-        'multiclassaccuracy_1': tensor(0.7500),
-        'multiclassaccuracy_2': tensor(0.)}
+         'multiclassaccuracy_1': tensor(0.7500),
+         'multiclassaccuracy_2': tensor(0.)}
 
     Example::
         Using custom name via prefix and postfix:
 
-        >>> import torch
-        >>> _ = torch.manual_seed(42)
+        >>> from torch import randint, randn
         >>> from torchmetrics.wrappers import ClasswiseWrapper
         >>> from torchmetrics.classification import MulticlassAccuracy
         >>> metric_pre = ClasswiseWrapper(MulticlassAccuracy(num_classes=3, average=None), prefix="acc-")
         >>> metric_post = ClasswiseWrapper(MulticlassAccuracy(num_classes=3, average=None), postfix="-acc")
-        >>> preds = torch.randn(10, 3).softmax(dim=-1)
-        >>> target = torch.randint(3, (10,))
+        >>> preds = randn(10, 3).softmax(dim=-1)
+        >>> target = randint(3, (10,))
         >>> metric_pre(preds, target)  # doctest: +NORMALIZE_WHITESPACE
-        {'acc-0': tensor(0.5000),
-         'acc-1': tensor(0.7500),
-         'acc-2': tensor(0.)}
+        {'acc-0': tensor(0.3333), 'acc-1': tensor(0.6667), 'acc-2': tensor(0.)}
         >>> metric_post(preds, target)  # doctest: +NORMALIZE_WHITESPACE
-        {'0-acc': tensor(0.5000),
-         '1-acc': tensor(0.7500),
-         '2-acc': tensor(0.)}
+        {'0-acc': tensor(0.3333), '1-acc': tensor(0.6667), '2-acc': tensor(0.)}
 
     Example::
         Providing labels as a list of strings:
 
+        >>> from torch import randint, randn
         >>> from torchmetrics.wrappers import ClasswiseWrapper
         >>> from torchmetrics.classification import MulticlassAccuracy
         >>> metric = ClasswiseWrapper(
         ...    MulticlassAccuracy(num_classes=3, average=None),
         ...    labels=["horse", "fish", "dog"]
         ... )
-        >>> preds = torch.randn(10, 3).softmax(dim=-1)
-        >>> target = torch.randint(3, (10,))
+        >>> preds = randn(10, 3).softmax(dim=-1)
+        >>> target = randint(3, (10,))
         >>> metric(preds, target)  # doctest: +NORMALIZE_WHITESPACE
-        {'multiclassaccuracy_horse': tensor(0.3333),
-        'multiclassaccuracy_fish': tensor(0.6667),
-        'multiclassaccuracy_dog': tensor(0.)}
+        {'multiclassaccuracy_horse': tensor(0.),
+         'multiclassaccuracy_fish': tensor(0.3333),
+         'multiclassaccuracy_dog': tensor(0.4000)}
 
     Example::
         Classwise can also be used in combination with :class:`~torchmetrics.MetricCollection`. In this case, everything
         will be flattened into a single dictionary:
 
+        >>> from torch import randint, randn
         >>> from torchmetrics import MetricCollection
         >>> from torchmetrics.wrappers import ClasswiseWrapper
         >>> from torchmetrics.classification import MulticlassAccuracy, MulticlassRecall
@@ -104,15 +100,15 @@ class ClasswiseWrapper(WrapperMetric):
         ...     {'multiclassaccuracy': ClasswiseWrapper(MulticlassAccuracy(num_classes=3, average=None), labels),
         ...     'multiclassrecall': ClasswiseWrapper(MulticlassRecall(num_classes=3, average=None), labels)}
         ... )
-        >>> preds = torch.randn(10, 3).softmax(dim=-1)
-        >>> target = torch.randint(3, (10,))
+        >>> preds = randn(10, 3).softmax(dim=-1)
+        >>> target = randint(3, (10,))
         >>> metric(preds, target)  # doctest: +NORMALIZE_WHITESPACE
-        {'multiclassaccuracy_horse': tensor(0.),
+        {'multiclassaccuracy_horse': tensor(0.6667),
          'multiclassaccuracy_fish': tensor(0.3333),
-         'multiclassaccuracy_dog': tensor(0.4000),
-         'multiclassrecall_horse': tensor(0.),
+         'multiclassaccuracy_dog': tensor(0.5000),
+         'multiclassrecall_horse': tensor(0.6667),
          'multiclassrecall_fish': tensor(0.3333),
-         'multiclassrecall_dog': tensor(0.4000)}
+         'multiclassrecall_dog': tensor(0.5000)}
 
     """
 
diff --git a/src/torchmetrics/wrappers/feature_share.py b/src/torchmetrics/wrappers/feature_share.py
index b1fe0451534..1bd1b81783b 100644
--- a/src/torchmetrics/wrappers/feature_share.py
+++ b/src/torchmetrics/wrappers/feature_share.py
@@ -68,7 +68,6 @@ class FeatureShare(MetricCollection):
 
     Example::
         >>> import torch
-        >>> _ = torch.manual_seed(42)
         >>> from torchmetrics.wrappers import FeatureShare
         >>> from torchmetrics.image import FrechetInceptionDistance, KernelInceptionDistance
         >>> # initialize the metrics
diff --git a/src/torchmetrics/wrappers/tracker.py b/src/torchmetrics/wrappers/tracker.py
index 2a32ee575fe..554902d1092 100644
--- a/src/torchmetrics/wrappers/tracker.py
+++ b/src/torchmetrics/wrappers/tracker.py
@@ -52,15 +52,14 @@ class MetricTracker(ModuleList):
             better (``True``) or lower is better (``False``).
 
     Example (single metric):
+        >>> from torch import randint
         >>> from torchmetrics.wrappers import MetricTracker
         >>> from torchmetrics.classification import MulticlassAccuracy
-        >>> _ = torch.manual_seed(42)
         >>> tracker = MetricTracker(MulticlassAccuracy(num_classes=10, average='micro'))
         >>> for epoch in range(5):
         ...     tracker.increment()
         ...     for batch_idx in range(5):
-        ...         preds, target = torch.randint(10, (100,)), torch.randint(10, (100,))
-        ...         tracker.update(preds, target)
+        ...         tracker.update(randint(10, (100,)), randint(10, (100,)))
         ...     print(f"current acc={tracker.compute()}")
         current acc=0.1120000034570694
         current acc=0.08799999952316284
@@ -76,32 +75,31 @@ class MetricTracker(ModuleList):
         tensor([0.1120, 0.0880, 0.1260, 0.0800, 0.1020])
 
     Example (multiple metrics using MetricCollection):
+        >>> from torch import randn
         >>> from torchmetrics.wrappers import MetricTracker
         >>> from torchmetrics import MetricCollection
         >>> from torchmetrics.regression import MeanSquaredError, ExplainedVariance
-        >>> _ = torch.manual_seed(42)
         >>> tracker = MetricTracker(MetricCollection([MeanSquaredError(), ExplainedVariance()]), maximize=[False, True])
         >>> for epoch in range(5):
         ...     tracker.increment()
         ...     for batch_idx in range(5):
-        ...         preds, target = torch.randn(100), torch.randn(100)
-        ...         tracker.update(preds, target)
+        ...         tracker.update(randn(100), randn(100))
         ...     print(f"current stats={tracker.compute()}")  # doctest: +NORMALIZE_WHITESPACE
-        current stats={'MeanSquaredError': tensor(1.8218), 'ExplainedVariance': tensor(-0.8969)}
-        current stats={'MeanSquaredError': tensor(2.0268), 'ExplainedVariance': tensor(-1.0206)}
-        current stats={'MeanSquaredError': tensor(1.9491), 'ExplainedVariance': tensor(-0.8298)}
-        current stats={'MeanSquaredError': tensor(1.9800), 'ExplainedVariance': tensor(-0.9199)}
-        current stats={'MeanSquaredError': tensor(2.2481), 'ExplainedVariance': tensor(-1.1622)}
+        current stats={'MeanSquaredError': tensor(2.3292), 'ExplainedVariance': tensor(-0.9516)}
+        current stats={'MeanSquaredError': tensor(2.1370), 'ExplainedVariance': tensor(-1.0775)}
+        current stats={'MeanSquaredError': tensor(2.1695), 'ExplainedVariance': tensor(-0.9945)}
+        current stats={'MeanSquaredError': tensor(2.1072), 'ExplainedVariance': tensor(-1.1878)}
+        current stats={'MeanSquaredError': tensor(2.0562), 'ExplainedVariance': tensor(-1.0754)}
         >>> from pprint import pprint
         >>> best_res, which_epoch = tracker.best_metric(return_step=True)
         >>> pprint(best_res)  # doctest: +ELLIPSIS
-        {'ExplainedVariance': -0.829...,
-         'MeanSquaredError': 1.821...}
+        {'ExplainedVariance': -0.951...,
+         'MeanSquaredError': 2.056...}
         >>> which_epoch
-        {'MeanSquaredError': 0, 'ExplainedVariance': 2}
+        {'MeanSquaredError': 4, 'ExplainedVariance': 0}
         >>> pprint(tracker.compute_all())
-        {'ExplainedVariance': tensor([-0.8969, -1.0206, -0.8298, -0.9199, -1.1622]),
-         'MeanSquaredError': tensor([1.8218, 2.0268, 1.9491, 1.9800, 2.2481])}
+        {'ExplainedVariance': tensor([-0.9516, -1.0775, -0.9945, -1.1878, -1.0754]),
+         'MeanSquaredError': tensor([2.3292, 2.1370, 2.1695, 2.1072, 2.0562])}
 
     """
 

From 99356f420bb62407bf5464407035bb57342ee7d3 Mon Sep 17 00:00:00 2001
From: jirka <jirka.borovec@seznam.cz>
Date: Thu, 29 Aug 2024 23:49:35 +0200
Subject: [PATCH 02/11] seed_all

---
 tests/unittests/segmentation/test_generalized_dice_score.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tests/unittests/segmentation/test_generalized_dice_score.py b/tests/unittests/segmentation/test_generalized_dice_score.py
index 2916ea6d443..f7e43ef2b56 100644
--- a/tests/unittests/segmentation/test_generalized_dice_score.py
+++ b/tests/unittests/segmentation/test_generalized_dice_score.py
@@ -21,8 +21,11 @@
 from torchmetrics.segmentation.generalized_dice import GeneralizedDiceScore
 
 from unittests import BATCH_SIZE, NUM_BATCHES, NUM_CLASSES, _Input
+from unittests._helpers import seed_all
 from unittests._helpers.testers import MetricTester
 
+seed_all(42)
+
 _inputs1 = _Input(
     preds=torch.randint(0, 2, (NUM_BATCHES, BATCH_SIZE, NUM_CLASSES, 16)),
     target=torch.randint(0, 2, (NUM_BATCHES, BATCH_SIZE, NUM_CLASSES, 16)),

From 015f3bc6626197f5b8de7faf9b29da30a7a48762 Mon Sep 17 00:00:00 2001
From: jirka <jirka.borovec@seznam.cz>
Date: Fri, 30 Aug 2024 00:12:53 +0200
Subject: [PATCH 03/11] tests

---
 src/torchmetrics/image/perceptual_path_length.py | 4 ++--
 src/torchmetrics/multimodal/clip_iqa.py          | 2 +-
 src/torchmetrics/multimodal/clip_score.py        | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/src/torchmetrics/image/perceptual_path_length.py b/src/torchmetrics/image/perceptual_path_length.py
index 4e8cca23343..dcfca43f8d5 100644
--- a/src/torchmetrics/image/perceptual_path_length.py
+++ b/src/torchmetrics/image/perceptual_path_length.py
@@ -112,9 +112,9 @@ class PerceptualPathLength(Metric):
         >>> generator = DummyGenerator(2)
         >>> ppl = PerceptualPathLength(num_samples=10)
         >>> ppl(generator)
-        (tensor(0.2369),
+        (tensor(0.2371),
          tensor(0.1760),
-         tensor([0.3489, 0.1363, 0.2535, 0.0907, 0.1785, 0.0769, 0.5864, 0.0691, 0.3920]))
+         tensor([0.3494, 0.1367, 0.2531, 0.0907, 0.1789, 0.0769, 0.5863, 0.0691, 0.3926]))
 
     """
 
diff --git a/src/torchmetrics/multimodal/clip_iqa.py b/src/torchmetrics/multimodal/clip_iqa.py
index 6ab75356047..4d0794a6425 100644
--- a/src/torchmetrics/multimodal/clip_iqa.py
+++ b/src/torchmetrics/multimodal/clip_iqa.py
@@ -143,7 +143,7 @@ class CLIPImageQualityAssessment(Metric):
         >>> imgs = randint(255, (2, 3, 224, 224)).float()
         >>> metric = CLIPImageQualityAssessment(prompts=("quality", "brightness"))
         >>> metric(imgs)
-        {'quality': tensor([0.8894, 0.8902]), 'brightness': tensor([0.5507, 0.5208])}
+        {'quality': tensor([0.8693, 0.8705]), 'brightness': tensor([0.5722, 0.4762])}
 
     Example::
         Custom prompts. Must always be a tuple of length 2, with a positive and negative prompt.
diff --git a/src/torchmetrics/multimodal/clip_score.py b/src/torchmetrics/multimodal/clip_score.py
index 47bcbe3b47f..14e5a8e2ec9 100644
--- a/src/torchmetrics/multimodal/clip_score.py
+++ b/src/torchmetrics/multimodal/clip_score.py
@@ -87,7 +87,7 @@ class CLIPScore(Metric):
         >>> metric = CLIPScore(model_name_or_path="openai/clip-vit-base-patch16")
         >>> score = metric(randint(255, (3, 224, 224)), "a photo of a cat")
         >>> score.detach()
-        tensor(24.4255)
+        tensor(24.8020)
 
     """
 

From 58274c87010e487f09413ca275a9fc89b76f616c Mon Sep 17 00:00:00 2001
From: jirka <jirka.borovec@seznam.cz>
Date: Fri, 30 Aug 2024 10:10:35 +0200
Subject: [PATCH 04/11] test

---
 src/torchmetrics/multimodal/clip_iqa.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/torchmetrics/multimodal/clip_iqa.py b/src/torchmetrics/multimodal/clip_iqa.py
index 4d0794a6425..7a66de4ae3e 100644
--- a/src/torchmetrics/multimodal/clip_iqa.py
+++ b/src/torchmetrics/multimodal/clip_iqa.py
@@ -153,7 +153,7 @@ class CLIPImageQualityAssessment(Metric):
         >>> imgs = randint(255, (2, 3, 224, 224)).float()
         >>> metric = CLIPImageQualityAssessment(prompts=(("Super good photo.", "Super bad photo."), "brightness"))
         >>> metric(imgs)
-        {'user_defined_0': tensor([0.9652, 0.9629]), 'brightness': tensor([0.5507, 0.5208])}
+        {'user_defined_0': tensor([0.9578, 0.9654]), 'brightness': tensor([0.5495, 0.5764])}
 
     """
 

From 112af41b911274d9d69cca520a402725e55c1bb6 Mon Sep 17 00:00:00 2001
From: jirka <jirka.borovec@seznam.cz>
Date: Fri, 30 Aug 2024 10:52:08 +0200
Subject: [PATCH 05/11] test

---
 src/torchmetrics/image/perceptual_path_length.py | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/src/torchmetrics/image/perceptual_path_length.py b/src/torchmetrics/image/perceptual_path_length.py
index dcfca43f8d5..4c312404934 100644
--- a/src/torchmetrics/image/perceptual_path_length.py
+++ b/src/torchmetrics/image/perceptual_path_length.py
@@ -99,7 +99,6 @@ class PerceptualPathLength(Metric):
 
     Example::
         >>> import torch
-        >>> from torchmetrics.image import PerceptualPathLength
         >>> class DummyGenerator(torch.nn.Module):
         ...    def __init__(self, z_size) -> None:
         ...       super().__init__()
@@ -112,9 +111,7 @@ class PerceptualPathLength(Metric):
         >>> generator = DummyGenerator(2)
         >>> ppl = PerceptualPathLength(num_samples=10)
         >>> ppl(generator)
-        (tensor(0.2371),
-         tensor(0.1760),
-         tensor([0.3494, 0.1367, 0.2531, 0.0907, 0.1789, 0.0769, 0.5863, 0.0691, 0.3926]))
+        (tensor(...), tensor(...), tensor([...]))
 
     """
 

From fcfdaea8864fd17a28a054945240dd6f4fe751a3 Mon Sep 17 00:00:00 2001
From: jirka <jirka.borovec@seznam.cz>
Date: Fri, 30 Aug 2024 11:18:41 +0200
Subject: [PATCH 06/11] test

---
 src/torchmetrics/image/perceptual_path_length.py | 4 ++--
 src/torchmetrics/multimodal/clip_score.py        | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/torchmetrics/image/perceptual_path_length.py b/src/torchmetrics/image/perceptual_path_length.py
index 4c312404934..e5873723f06 100644
--- a/src/torchmetrics/image/perceptual_path_length.py
+++ b/src/torchmetrics/image/perceptual_path_length.py
@@ -23,9 +23,9 @@
     perceptual_path_length,
 )
 from torchmetrics.metric import Metric
-from torchmetrics.utilities.imports import _TORCHVISION_AVAILABLE
+from torchmetrics.utilities.imports import _TORCHVISION_AVAILABLE, _TORCH_GREATER_EQUAL_2_0
 
-if not _TORCHVISION_AVAILABLE:
+if not _TORCHVISION_AVAILABLE or not _TORCH_GREATER_EQUAL_2_0:
     __doctest_skip__ = ["PerceptualPathLength"]
 
 
diff --git a/src/torchmetrics/multimodal/clip_score.py b/src/torchmetrics/multimodal/clip_score.py
index 14e5a8e2ec9..16a90c84168 100644
--- a/src/torchmetrics/multimodal/clip_score.py
+++ b/src/torchmetrics/multimodal/clip_score.py
@@ -86,7 +86,7 @@ class CLIPScore(Metric):
         >>> from torchmetrics.multimodal.clip_score import CLIPScore
         >>> metric = CLIPScore(model_name_or_path="openai/clip-vit-base-patch16")
         >>> score = metric(randint(255, (3, 224, 224)), "a photo of a cat")
-        >>> score.detach()
+        >>> score.detach().round(decimals=3)
         tensor(24.8020)
 
     """

From 87d27a36b2d87f129c72190bc950bd46973355e8 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Fri, 30 Aug 2024 09:19:05 +0000
Subject: [PATCH 07/11] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 src/torchmetrics/image/perceptual_path_length.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/torchmetrics/image/perceptual_path_length.py b/src/torchmetrics/image/perceptual_path_length.py
index e5873723f06..b2255941250 100644
--- a/src/torchmetrics/image/perceptual_path_length.py
+++ b/src/torchmetrics/image/perceptual_path_length.py
@@ -23,7 +23,7 @@
     perceptual_path_length,
 )
 from torchmetrics.metric import Metric
-from torchmetrics.utilities.imports import _TORCHVISION_AVAILABLE, _TORCH_GREATER_EQUAL_2_0
+from torchmetrics.utilities.imports import _TORCH_GREATER_EQUAL_2_0, _TORCHVISION_AVAILABLE
 
 if not _TORCHVISION_AVAILABLE or not _TORCH_GREATER_EQUAL_2_0:
     __doctest_skip__ = ["PerceptualPathLength"]

From a9b004cd7481fe167b31e20ff84444408fa4402c Mon Sep 17 00:00:00 2001
From: jirka <jirka.borovec@seznam.cz>
Date: Fri, 30 Aug 2024 11:41:42 +0200
Subject: [PATCH 08/11] test

---
 src/torchmetrics/multimodal/clip_score.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/torchmetrics/multimodal/clip_score.py b/src/torchmetrics/multimodal/clip_score.py
index 16a90c84168..5a63b96530e 100644
--- a/src/torchmetrics/multimodal/clip_score.py
+++ b/src/torchmetrics/multimodal/clip_score.py
@@ -86,7 +86,7 @@ class CLIPScore(Metric):
         >>> from torchmetrics.multimodal.clip_score import CLIPScore
         >>> metric = CLIPScore(model_name_or_path="openai/clip-vit-base-patch16")
         >>> score = metric(randint(255, (3, 224, 224)), "a photo of a cat")
-        >>> score.detach().round(decimals=3)
+        >>> score.round(decimals=3).detach()
         tensor(24.8020)
 
     """

From 5a31692a7985401ed78c4b41f8ad15ae5d007f44 Mon Sep 17 00:00:00 2001
From: jirka <jirka.borovec@seznam.cz>
Date: Fri, 30 Aug 2024 12:00:54 +0200
Subject: [PATCH 09/11] test

---
 src/torchmetrics/multimodal/clip_score.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/torchmetrics/multimodal/clip_score.py b/src/torchmetrics/multimodal/clip_score.py
index 5a63b96530e..4c6bbc7482d 100644
--- a/src/torchmetrics/multimodal/clip_score.py
+++ b/src/torchmetrics/multimodal/clip_score.py
@@ -82,11 +82,11 @@ class CLIPScore(Metric):
             If transformers package is not installed or version is lower than 4.10.0
 
     Example:
-        >>> from torch import randint
+        >>> from torch import randint, round
         >>> from torchmetrics.multimodal.clip_score import CLIPScore
         >>> metric = CLIPScore(model_name_or_path="openai/clip-vit-base-patch16")
         >>> score = metric(randint(255, (3, 224, 224)), "a photo of a cat")
-        >>> score.round(decimals=3).detach()
+        >>> round(score.detach(), decimals=3)
         tensor(24.8020)
 
     """

From 5da59ab9fb82bb209bf3965b0546eb0e86163eb9 Mon Sep 17 00:00:00 2001
From: jirka <jirka.borovec@seznam.cz>
Date: Fri, 30 Aug 2024 12:24:53 +0200
Subject: [PATCH 10/11] test

---
 src/torchmetrics/multimodal/clip_score.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/torchmetrics/multimodal/clip_score.py b/src/torchmetrics/multimodal/clip_score.py
index 4c6bbc7482d..0ec5d83ec3a 100644
--- a/src/torchmetrics/multimodal/clip_score.py
+++ b/src/torchmetrics/multimodal/clip_score.py
@@ -86,7 +86,7 @@ class CLIPScore(Metric):
         >>> from torchmetrics.multimodal.clip_score import CLIPScore
         >>> metric = CLIPScore(model_name_or_path="openai/clip-vit-base-patch16")
         >>> score = metric(randint(255, (3, 224, 224)), "a photo of a cat")
-        >>> round(score.detach(), decimals=3)
+        >>> score.detach().round(decimals=3)
         tensor(24.8020)
 
     """

From f7ccd50c2dc89203813577129d8f5b83b9391d40 Mon Sep 17 00:00:00 2001
From: jirka <jirka.borovec@seznam.cz>
Date: Fri, 30 Aug 2024 12:42:14 +0200
Subject: [PATCH 11/11] test

---
 src/torchmetrics/multimodal/clip_score.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/torchmetrics/multimodal/clip_score.py b/src/torchmetrics/multimodal/clip_score.py
index 0ec5d83ec3a..f385fbc145d 100644
--- a/src/torchmetrics/multimodal/clip_score.py
+++ b/src/torchmetrics/multimodal/clip_score.py
@@ -82,12 +82,12 @@ class CLIPScore(Metric):
             If transformers package is not installed or version is lower than 4.10.0
 
     Example:
-        >>> from torch import randint, round
+        >>> from torch import randint
         >>> from torchmetrics.multimodal.clip_score import CLIPScore
         >>> metric = CLIPScore(model_name_or_path="openai/clip-vit-base-patch16")
         >>> score = metric(randint(255, (3, 224, 224)), "a photo of a cat")
-        >>> score.detach().round(decimals=3)
-        tensor(24.8020)
+        >>> score.detach().round()
+        tensor(25.)
 
     """