From e9d2455be18c2c30e42da04e57367b24aa1cbf58 Mon Sep 17 00:00:00 2001
From: sl_wang <wangshuangling1@huawei.com>
Date: Wed, 23 Jun 2021 11:27:52 +0800
Subject: [PATCH] adjust api format

---
 mindspore/nn/optim/thor.py                  | 12 ++++++------
 mindspore/train/train_thor/convert_utils.py |  2 ++
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/mindspore/nn/optim/thor.py b/mindspore/nn/optim/thor.py
index 67091f618c3..98b484ce61c 100644
--- a/mindspore/nn/optim/thor.py
+++ b/mindspore/nn/optim/thor.py
@@ -209,12 +209,12 @@ def thor(net, learning_rate, damping, momentum, weight_decay=0.0, loss_scale=1.0
     The updating formulas are as follows,
 
     .. math::
-    \begin{array}{ll} \\
-        A_i = a_i{a_i}^T \\
-        G_i = D_{s_i}{ D_{s_i}}^T \\
-        m_i = \beta * m_i + ({G_i^{(k)}}+\lambda I)^{-1}) g_i ({\overline A_{i-1}^{(k)}}+\lambda I)^{-1} \\
-        w_i = w_i - \alpha * m_i \\
-    \end{array}
+        \begin{array}{ll} \\
+            A_i = a_i{a_i}^T \\
+            G_i = D_{s_i}{ D_{s_i}}^T \\
+            m_i = \beta * m_i + ({G_i^{(k)}}+\lambda I)^{-1}) g_i ({\overline A_{i-1}^{(k)}}+\lambda I)^{-1} \\
+            w_i = w_i - \alpha * m_i \\
+        \end{array}
 
     :math:`D_{s_i}` represents the derivative of the loss function of the output of the i-th layer,
     :math:`a_{i-1}` represents the input of i-th layer,and which is the activations of previous layer,
diff --git a/mindspore/train/train_thor/convert_utils.py b/mindspore/train/train_thor/convert_utils.py
index fd5609e9928..9c8d20da0e2 100644
--- a/mindspore/train/train_thor/convert_utils.py
+++ b/mindspore/train/train_thor/convert_utils.py
@@ -167,12 +167,14 @@ class ConvertModelUtils():
             metrics (Union[dict, set]): A Dictionary or a set of metrics to be evaluated by the model during
                                         training. eg: {'accuracy', 'recall'}. Default: None.
             amp_level (str): Level for mixed precision training. Supports ["O0", "O2", "O3", "auto"]. Default: "O0".
+
                 - O0: Do not change.
                 - O2: Cast network to float16, keep batchnorm run in float32, using dynamic loss scale.
                 - O3: Cast network to float16, with additional property 'keep_batchnorm_fp32=False'.
                 - auto: Set level to recommended level in different devices. O2 is recommended on GPU, O3 is
                   recommended on Ascend. The recommended level is based on the expert experience, cannot
                   always generalize. User should specify the level for special network.
+
             loss_scale_manager (Union[None, LossScaleManager]): If it is None, the loss would not be scaled.
                 Otherwise, scale the loss by LossScaleManager and optimizer can not be None. It is a key argument.
                 e.g. Use `loss_scale_manager=None` to set the value.