diff --git a/mindspore/nn/layer/image.py b/mindspore/nn/layer/image.py
index ea9964ea5b..3fee77f995 100644
--- a/mindspore/nn/layer/image.py
+++ b/mindspore/nn/layer/image.py
@@ -349,7 +349,7 @@ class PSNR(Cell):
 
     Args:
         max_val (Union[int, float]): The dynamic range of the pixel values (255 for 8-bit grayscale images).
-          Default: 1.0.
+          The value must be greater than 0. Default: 1.0.
 
     Inputs:
         - **img1** (Tensor) - The first image batch with format 'NCHW'. It must be the same shape and dtype as img2.
diff --git a/mindspore/ops/composite/random_ops.py b/mindspore/ops/composite/random_ops.py
index 4a41cb4507..4871e52806 100644
--- a/mindspore/ops/composite/random_ops.py
+++ b/mindspore/ops/composite/random_ops.py
@@ -247,12 +247,11 @@ def multinomial(inputs, num_sample, replacement=True, seed=0):
 
     Args:
         inputs (Tensor): The input tensor containing probabilities, must be 1 or 2 dimensions, with
-        float32 data type.
+          float32 data type.
         num_sample (int): Number of samples to draw.
         replacement (bool, optional): Whether to draw with replacement or not, default True.
         seed (int, optional): Seed is used as entropy source for the random number engines to generate
-        pseudo-random numbers,
-          must be non-negative. Default: 0.
+          pseudo-random numbers, must be non-negative. Default: 0.
 
     Outputs:
         Tensor, has the same rows with input. The number of sampled indices of each row is `num_samples`.
diff --git a/mindspore/ops/operations/nn_ops.py b/mindspore/ops/operations/nn_ops.py
index 6724a0ab78..8a3dae0943 100644
--- a/mindspore/ops/operations/nn_ops.py
+++ b/mindspore/ops/operations/nn_ops.py
@@ -2488,7 +2488,7 @@ class ResizeBilinear(PrimitiveWithInfer):
 
     Inputs:
         - **input** (Tensor) - Image to be resized. Input images must be a 4-D tensor with shape
-         [batch, channels, height, width], with data type of float32 or float16.
+          :math:`(batch, channels, height, width)`, with data type of float32 or float16.
 
     Outputs:
         Tensor, resized image. 4-D with shape [batch, channels, new_height, new_width] in `float32`.