diff --git a/tutorials/source_en/beginner/autograd.md b/tutorials/source_en/beginner/autograd.md
index b75dac525d3088d23e2b5c6813b6dfab02e53ff6..c1ed3df5a36b779d0b90cc0fc9ebaf9c64388aa0 100644
--- a/tutorials/source_en/beginner/autograd.md
+++ b/tutorials/source_en/beginner/autograd.md
@@ -11,9 +11,7 @@ MindSpore uses the design philosophy of functional auto-differentiation to provi
 ```python
 import numpy as np
 import mindspore
-from mindspore import nn
-from mindspore import ops
-from mindspore import Tensor, Parameter
+from mindspore import ops, nn, Tensor, Parameter
 ```
 
 ## Functions and Computing Graphs
@@ -25,6 +23,7 @@ Computing graphs are a way to represent mathematical functions in a graph-theore
 In this model, $x$ is the input, $y$ is the correct value, and $w$ and $b$ are the parameters we need to optimize.
 
 ```python
+np.random.seed(42)
 x = ops.ones(5, mindspore.float32)  # input tensor
 y = ops.zeros(3, mindspore.float32)  # expected output
 w = Parameter(Tensor(np.random.randn(5, 3), mindspore.float32), name='w') # weight
@@ -51,7 +50,7 @@ print(loss)
 ```
 
 ```text
-0.914285
+1.342315
 ```
 
 ## Differential Functions and Gradient Computing
@@ -80,12 +79,12 @@ print(grads)
 
 ```text
 (Tensor(shape=[5, 3], dtype=Float32, value=
- [[ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],
-  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],
-  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],
-  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],
-  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01]]),
- Tensor(shape=[3], dtype=Float32, value= [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01]))
+ [[ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],
+  [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],
+  [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],
+  [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],
+  [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02]]),
+ Tensor(shape=[3], dtype=Float32, value= [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02]))
 ```
 
 ## Stop Gradient
@@ -134,12 +133,12 @@ print(grads)
 
 ```text
 (Tensor(shape=[5, 3], dtype=Float32, value=
- [[ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],
-  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],
-  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],
-  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],
-  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01]]),
- Tensor(shape=[3], dtype=Float32, value= [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01]))
+ [[ 1.32618928e+00,  1.01589143e+00,  1.04216456e+00],
+  [ 1.32618928e+00,  1.01589143e+00,  1.04216456e+00],
+  [ 1.32618928e+00,  1.01589143e+00,  1.04216456e+00],
+  [ 1.32618928e+00,  1.01589143e+00,  1.04216456e+00],
+  [ 1.32618928e+00,  1.01589143e+00,  1.04216456e+00]]),
+ Tensor(shape=[3], dtype=Float32, value= [ 1.32618928e+00,  1.01589143e+00,  1.04216456e+00]))
 ```
 
 It can be seen that the gradient values corresponding to $w$ and $b$ are the same as the gradient values found by the initial `function`.
@@ -162,14 +161,14 @@ print(grads, z)
 ```
 
 ```text
-((Tensor(shape=[5, 3], dtype=Float32, value=
-  [[ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],
-   [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],
-   [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],
-   [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],
-   [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01]]),
-  Tensor(shape=[3], dtype=Float32, value= [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01])),
- Tensor(shape=[3], dtype=Float32, value= [-1.40476596e+00, -1.64932394e+00,  2.24711204e+00]))
+(Tensor(shape=[5, 3], dtype=Float32, value=
+ [[ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],
+  [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],
+  [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],
+  [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],
+  [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02]]),
+ Tensor(shape=[3], dtype=Float32, value= [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02]))
+[ 3.8211915 -2.994512  -1.932323 ]
 ```
 
 ## Calculating Neural Network Gradient
@@ -225,12 +224,12 @@ print(grads)
 
 ```text
 (Tensor(shape=[5, 3], dtype=Float32, value=
- [[ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],
-  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],
-  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],
-  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],
-  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01]]),
- Tensor(shape=[3], dtype=Float32, value= [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01]))
+ [[ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],
+  [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],
+  [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],
+  [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],
+  [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02]]),
+ Tensor(shape=[3], dtype=Float32, value= [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02]))
 ```
 
 Executing the differentiation function, and we can see that the gradient value is the same as the gradient value obtained from the previous `function`.
diff --git a/tutorials/source_zh_cn/beginner/autograd.ipynb b/tutorials/source_zh_cn/beginner/autograd.ipynb
index 3fb096cb262988631c111dee8a5f6f5d17b33d82..8c952b9d4d346b1616cb63af82a1ffba357e07b1 100644
--- a/tutorials/source_zh_cn/beginner/autograd.ipynb
+++ b/tutorials/source_zh_cn/beginner/autograd.ipynb
@@ -28,9 +28,7 @@
    "source": [
     "import numpy as np\n",
     "import mindspore\n",
-    "from mindspore import nn\n",
-    "from mindspore import ops\n",
-    "from mindspore import Tensor, Parameter"
+    "from mindspore import ops, nn, Tensor, Parameter"
    ]
   },
   {
@@ -57,6 +55,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "np.random.seed(42)\n",
     "x = ops.ones(5, mindspore.float32)  # input tensor\n",
     "y = ops.zeros(3, mindspore.float32)  # expected output\n",
     "w = Parameter(Tensor(np.random.randn(5, 3), mindspore.float32), name='w') # weight\n",
@@ -96,14 +95,11 @@
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "0.914285"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1.3423151\n"
+     ]
     }
    ],
    "source": [
@@ -156,20 +152,16 @@
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "(Tensor(shape=[5, 3], dtype=Float32, value=\n",
-       " [[ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],\n",
-       "  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],\n",
-       "  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],\n",
-       "  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],\n",
-       "  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01]]),\n",
-       " Tensor(shape=[3], dtype=Float32, value= [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01]))"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(Tensor(shape=[5, 3], dtype=Float32, value=\n",
+      "[[ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],\n",
+      " [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],\n",
+      " [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],\n",
+      " [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],\n",
+      " [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02]]), Tensor(shape=[3], dtype=Float32, value= [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02]))\n"
+     ]
     }
    ],
    "source": [
@@ -211,20 +203,16 @@
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "(Tensor(shape=[5, 3], dtype=Float32, value=\n",
-       " [[ 1.06568694e+00,  1.05373347e+00,  1.30146706e+00],\n",
-       "  [ 1.06568694e+00,  1.05373347e+00,  1.30146706e+00],\n",
-       "  [ 1.06568694e+00,  1.05373347e+00,  1.30146706e+00],\n",
-       "  [ 1.06568694e+00,  1.05373347e+00,  1.30146706e+00],\n",
-       "  [ 1.06568694e+00,  1.05373347e+00,  1.30146706e+00]]),\n",
-       " Tensor(shape=[3], dtype=Float32, value= [ 1.06568694e+00,  1.05373347e+00,  1.30146706e+00]))"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(Tensor(shape=[5, 3], dtype=Float32, value=\n",
+      "[[ 1.32618928e+00,  1.01589143e+00,  1.04216456e+00],\n",
+      " [ 1.32618928e+00,  1.01589143e+00,  1.04216456e+00],\n",
+      " [ 1.32618928e+00,  1.01589143e+00,  1.04216456e+00],\n",
+      " [ 1.32618928e+00,  1.01589143e+00,  1.04216456e+00],\n",
+      " [ 1.32618928e+00,  1.01589143e+00,  1.04216456e+00]]), Tensor(shape=[3], dtype=Float32, value= [ 1.32618928e+00,  1.01589143e+00,  1.04216456e+00]))\n"
+     ]
     }
    ],
    "source": [
@@ -258,20 +246,16 @@
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "(Tensor(shape=[5, 3], dtype=Float32, value=\n",
-       " [[ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],\n",
-       "  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],\n",
-       "  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],\n",
-       "  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],\n",
-       "  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01]]),\n",
-       " Tensor(shape=[3], dtype=Float32, value= [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01]))"
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(Tensor(shape=[5, 3], dtype=Float32, value=\n",
+      "[[ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],\n",
+      " [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],\n",
+      " [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],\n",
+      " [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],\n",
+      " [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02]]), Tensor(shape=[3], dtype=Float32, value= [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02]))\n"
+     ]
     }
    ],
    "source": [
@@ -315,21 +299,16 @@
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "((Tensor(shape=[5, 3], dtype=Float32, value=\n",
-       "  [[ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],\n",
-       "   [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],\n",
-       "   [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],\n",
-       "   [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],\n",
-       "   [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01]]),\n",
-       "  Tensor(shape=[3], dtype=Float32, value= [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01])),\n",
-       " Tensor(shape=[3], dtype=Float32, value= [-1.40476596e+00, -1.64932394e+00,  2.24711204e+00]))"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(Tensor(shape=[5, 3], dtype=Float32, value=\n",
+      "[[ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],\n",
+      " [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],\n",
+      " [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],\n",
+      " [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],\n",
+      " [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02]]), Tensor(shape=[3], dtype=Float32, value= [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02])) [ 3.8211915 -2.994512  -1.932323 ]\n"
+     ]
     }
    ],
    "source": [
@@ -441,20 +420,16 @@
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "(Tensor(shape=[5, 3], dtype=Float32, value=\n",
-       " [[ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],\n",
-       "  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],\n",
-       "  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],\n",
-       "  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01],\n",
-       "  [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01]]),\n",
-       " Tensor(shape=[3], dtype=Float32, value= [ 6.56869709e-02,  5.37334494e-02,  3.01467031e-01]))"
-      ]
-     },
-     "execution_count": 17,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(Tensor(shape=[5, 3], dtype=Float32, value=\n",
+      "[[ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],\n",
+      " [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],\n",
+      " [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],\n",
+      " [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02],\n",
+      " [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02]]), Tensor(shape=[3], dtype=Float32, value= [ 3.26189250e-01,  1.58914644e-02,  4.21645455e-02]))\n"
+     ]
     }
    ],
    "source": [
@@ -472,9 +447,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "MindSpore",
+   "display_name": "ms25-kernel",
    "language": "python",
-   "name": "mindspore"
+   "name": "ms25-kernel"
   },
   "language_info": {
    "codemirror_mode": {
@@ -486,7 +461,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.5"
+   "version": "3.9.21"
   },
   "vscode": {
    "interpreter": {