docs(mge): fix docstring in loss and dataset

GitOrigin-RevId: 6b566734157eaeaa176f735254ac5e8bba96914f

python_module/megengine/data/dataset/vision/imagenet.py

@@ -69,20 +69,26 @@ class ImageNet(ImageFolder):
     """
 
     def __init__(self, root: str = None, train: bool = True, **kwargs):
-        r"""initilization
+        r"""
+        initialization:
 
-        if ``root`` contains ``self.target_folder`` depent on ``train``:
-            initialize ImageFolder with target_folder
-        else:
-            if all raw files are in ``root``:
-                parse ``self.target_folder`` from raw files
-                initialize ImageFolder with ``self.target_folder``
-            else:
-                raise error
+        * if ``root`` contains ``self.target_folder`` depent on ``train``:
+
+          * initialize ImageFolder with target_folder
+
+        * else:
+
+          * if all raw files are in ``root``:
+
+            * parse ``self.target_folder`` from raw files
+            * initialize ImageFolder with ``self.target_folder``
+
+          * else:
+
+            * raise error
 
         :param root: root directory of imagenet data, if root is ``None``, used default_dataset_root
         :param train: if ``True``, load the train split, otherwise load the validation split
-        :param **kwarg: other keyword arguments for ImageFolder init
         """
 
         # process the root path

python_module/megengine/data/transform/vision/transform.py

@@ -50,29 +50,25 @@ class VisionTransform(Transform):
 
     :param order: Input type order. Input is a tuple contains different structures,
         order is used to specify the order of structures. For example, if your input
-        is (image, boxes) type, then the order should be ("image", "boxes"). 
+        is (image, boxes) type, then the order should be ("image", "boxes").
         Current available strings & data type are describe below:
-            "image": 
-                input image, with shape of (H, W, C)
-            "coords": 
-                coordinates, with shape of (N, 2)
-            "boxes": 
-                bounding boxes, with shape of (N, 4), "xyxy" format,
-                the 1st "xy" represents top left point of a box,
-                the 2nd "xy" represents right bottom point.
-            "mask": 
-                map used for segmentation, with shape of (H, W, 1)
-            "keypoints": 
-                keypoints with shape of (N, K, 3), N for number of instances, and K for number of keypoints in one instance. The first two dimensions
-                of last axis is coordinate of keypoints and the the 3rd dimension is
-                the label of keypoints.
-            "polygons": A sequence contains numpy array, its length is number of instances.
-                Each numpy array represents polygon coordinate of one instance.
-            "category": categories for some data type. For example, "image_category"
-                means category of the input image and "boxes_category" means categories of
-                bounding boxes.
-            "info": 
-                information for images such as image shapes and image path.
+
+        * "image": input image, with shape of (H, W, C)
+        * "coords": coordinates, with shape of (N, 2)
+        * "boxes": bounding boxes, with shape of (N, 4), "xyxy" format,
+          the 1st "xy" represents top left point of a box,
+          the 2nd "xy" represents right bottom point.
+        * "mask": map used for segmentation, with shape of (H, W, 1)
+        * "keypoints": keypoints with shape of (N, K, 3), N for number of instances,
+          and K for number of keypoints in one instance. The first two dimensions
+          of last axis is coordinate of keypoints and the the 3rd dimension is
+          the label of keypoints.
+        * "polygons": A sequence contains numpy array, its length is number of instances.
+          Each numpy array represents polygon coordinate of one instance.
+        * "category": categories for some data type. For example, "image_category"
+          means category of the input image and "boxes_category" means categories of
+          bounding boxes.
+        * "info": information for images such as image shapes and image path.
 
         You can also customize your data types only if you implement the corresponding
         _apply_*() methods, otherwise ``NotImplementedError`` will be raised.
@@ -356,7 +352,7 @@ class Resize(VisionTransform):
 
     :param output_size: Target size of image, with (height, width) shape.
     :param interpolation: Interpolation method. All methods are listed below:
-        
+
         * cv2.INTER_NEAREST – a nearest-neighbor interpolation.
         * cv2.INTER_LINEAR – a bilinear interpolation (used by default).
         * cv2.INTER_AREA – resampling using pixel area relation.

python_module/megengine/functional/loss.py

@@ -117,8 +117,8 @@ def cross_entropy(
         import numpy as np
         from megengine import tensor
         import megengine.functional as F
-        
-        
+
+
         data_shape = (1, 2)
         label_shape = (1, )
 
@@ -156,8 +156,10 @@ def cross_entropy_with_softmax(
     It has better numerical stability compared with sequential calls to :func:`~.softmax` and :func:`~.cross_entropy`.
 
     When using label smoothing, the label distribution is as follows:
+
     .. math::
         y^{LS}_{k}=y_{k}\left(1-\alpha\right)+\alpha/K
+
     where :math:`y^{LS}` and :math:`y` are new label distribution and origin label distribution respectively.
     k is the index of label distribution. :math:`\alpha` is label_smooth and :math:`K` is the number of classes.
 
@@ -197,7 +199,7 @@ def triplet_margin_loss(
     Creates a criterion that measures the triplet loss given an input tensors.
 
     .. math::
-        L(a, p, n) = max\left\{d\left(a_{i},p_{i}\right)-d\left(a_{i}, n_{i}\right)+margin, 0\right\},\ 
+        L(a, p, n) = max\left\{d\left(a_{i},p_{i}\right)-d\left(a_{i}, n_{i}\right)+margin, 0\right\},\
         d\left(x_{i},y_{i}\right)=\left\|x_{i}-y_{i}\right\|_{p}
 
     :param anchor: The input tensor representing the anchor samples.