[Enhancement] Add codespell pre-commit hook and fix typos (#920)

* add codespell pre-commit hook and fix typos

* Update mmseg/models/decode_heads/dpt_head.py

* Update mmseg/models/backbones/vit.py

* Update mmseg/models/backbones/vit.py

* fix typos

* skip formating typo

* deprecate formating

* skip ipynb

* unstage ipynb changes

* unstage ipynb changes

* fix typos in ipynb

* unstage ipynb changes

.github/ISSUE_TEMPLATE/config.yml

@@ -3,4 +3,4 @@ blank_issues_enabled: false
 contact_links:
   - name: MMSegmentation Documentation
     url: https://mmsegmentation.readthedocs.io
-    about: Check the docs and FAQ to see if you question is already anwsered.
+    about: Check the docs and FAQ to see if you question is already answered.

.github/ISSUE_TEMPLATE/error-report.md

@@ -30,7 +30,7 @@ A clear and concise description of what the bug is.
 
 **Environment**
 
-1. Please run `python mmseg/utils/collect_env.py` to collect necessary environment infomation and paste it here.
+1. Please run `python mmseg/utils/collect_env.py` to collect necessary environment information and paste it here.
 2. You may add addition that may be helpful for locating the problem, such as
     - How you installed PyTorch [e.g., pip, conda, source]
     - Other environment variables that may be related (such as `$PATH`, `$LD_LIBRARY_PATH`, `$PYTHONPATH`, etc.)

.pre-commit-config.yaml

@@ -34,6 +34,10 @@ repos:
     hooks:
       - id: markdownlint
         args: ["-r", "~MD002,~MD013,~MD029,~MD033,~MD034,~MD036"]
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.1.0
+    hooks:
+      - id: codespell
   - repo: https://github.com/myint/docformatter
     rev: v1.3.1
     hooks:

README.md

@@ -124,7 +124,7 @@ Please refer to [get_started.md](docs/get_started.md#installation) for installat
 
 Please see [train.md](docs/train.md) and [inference.md](docs/inference.md) for the basic usage of MMSegmentation.
 There are also tutorials for [customizing dataset](docs/tutorials/customize_datasets.md), [designing data pipeline](docs/tutorials/data_pipeline.md), [customizing modules](docs/tutorials/customize_models.md), and [customizing runtime](docs/tutorials/customize_runtime.md).
-We also provide many [training tricks](docs/tutorials/training_tricks.md) for better training and [usefule tools](docs/useful_tools.md) for deployment.
+We also provide many [training tricks](docs/tutorials/training_tricks.md) for better training and [useful tools](docs/useful_tools.md) for deployment.
 
 A Colab tutorial is also provided. You may preview the notebook [here](demo/MMSegmentation_Tutorial.ipynb) or directly [run](https://colab.research.google.com/github/open-mmlab/mmsegmentation/blob/master/demo/MMSegmentation_Tutorial.ipynb) on Colab.
 

docs/tutorials/config.md

@@ -67,7 +67,7 @@ model = dict(
         channels=512,  # The intermediate channels of decode head.
         pool_scales=(1, 2, 3, 6),  # The avg pooling scales of PSPHead. Please refer to paper for details.
         dropout_ratio=0.1,  # The dropout ratio before final classification layer.
-        num_classes=19,  # Number of segmentation classs. Usually 19 for cityscapes, 21 for VOC, 150 for ADE20k.
+        num_classes=19,  # Number of segmentation class. Usually 19 for cityscapes, 21 for VOC, 150 for ADE20k.
         norm_cfg=dict(type='SyncBN', requires_grad=True),  # The configuration of norm layer.
         align_corners=False,  # The align_corners argument for resize in decoding.
         loss_decode=dict(  # Config of loss function for the decode_head.
@@ -82,7 +82,7 @@ model = dict(
         num_convs=1,  # Number of convs in FCNHead. It is usually 1 in auxiliary head.
         concat_input=False,  # Whether concat output of convs with input before classification layer.
         dropout_ratio=0.1,  # The dropout ratio before final classification layer.
-        num_classes=19,  # Number of segmentation classs. Usually 19 for cityscapes, 21 for VOC, 150 for ADE20k.
+        num_classes=19,  # Number of segmentation class. Usually 19 for cityscapes, 21 for VOC, 150 for ADE20k.
         norm_cfg=dict(type='SyncBN', requires_grad=True),  # The configuration of norm layer.
         align_corners=False,  # The align_corners argument for resize in decoding.
         loss_decode=dict(  # Config of loss function for the decode_head.
@@ -132,7 +132,7 @@ test_pipeline = [
         flip=False,  # Whether to flip images during testing
         transforms=[
             dict(type='Resize',  # Use resize augmentation
-                 keep_ratio=True),  # Whether to keep the ratio between height and width, the img_scale set here will be supressed by the img_scale set above.
+                 keep_ratio=True),  # Whether to keep the ratio between height and width, the img_scale set here will be suppressed by the img_scale set above.
             dict(type='RandomFlip'),  # Thought RandomFlip is added in pipeline, it is not used when flip=False
             dict(
                 type='Normalize',  # Normalization config, the values are from img_norm_cfg
@@ -245,7 +245,7 @@ runner = dict(
 checkpoint_config = dict(  # Config to set the checkpoint hook, Refer to https://github.com/open-mmlab/mmcv/blob/master/mmcv/runner/hooks/checkpoint.py for implementation.
     by_epoch=False,  # Whether count by epoch or not.
     interval=4000)  # The save interval.
-evaluation = dict(  # The config to build the evaluation hook. Please refer to mmseg/core/evaulation/eval_hook.py for details.
+evaluation = dict(  # The config to build the evaluation hook. Please refer to mmseg/core/evaluation/eval_hook.py for details.
     interval=4000,  # The interval of evaluation.
     metric='mIoU')  # The evaluation metric.
 

docs/tutorials/customize_runtime.md

@@ -113,7 +113,7 @@ Tricks not implemented by the optimizer should be implemented through optimizer
         _delete_=True, grad_clip=dict(max_norm=35, norm_type=2))
     ```
 
-    If your config inherits the base config which already sets the `optimizer_config`, you might need `_delete_=True` to overide the unnecessary settings. See the [config documenetation](https://mmsegmentation.readthedocs.io/en/latest/config.html) for more details.
+    If your config inherits the base config which already sets the `optimizer_config`, you might need `_delete_=True` to override the unnecessary settings. See the [config documentation](https://mmsegmentation.readthedocs.io/en/latest/config.html) for more details.
 
 - __Use momentum schedule to accelerate model convergence__:
     We support momentum scheduler to modify model's momentum according to learning rate, which could make the model converge in a faster way.
@@ -198,7 +198,7 @@ custom_hooks = [
 
 ### Modify default runtime hooks
 
-There are some common hooks that are not registerd through `custom_hooks`, they are
+There are some common hooks that are not registered through `custom_hooks`, they are
 
 - log_config
 - checkpoint_config

docs_zh-CN/tutorials/config.md

@@ -241,7 +241,7 @@ runner = dict(
 checkpoint_config = dict(  # 设置检查点钩子 (checkpoint hook) 的配置文件。执行时请参考 https://github.com/open-mmlab/mmcv/blob/master/mmcv/runner/hooks/checkpoint.py。
     by_epoch=False,  # 是否按照每个 epoch 去算 runner。
     interval=4000)  # 保存的间隔
-evaluation = dict(  # 构建评估钩 (evaluation hook) 的配置文件。细节请参考 mmseg/core/evaulation/eval_hook.py。
+evaluation = dict(  # 构建评估钩 (evaluation hook) 的配置文件。细节请参考 mmseg/core/evaluation/eval_hook.py。
     interval=4000,  # 评估的间歇点
     metric='mIoU')  # 评估的指标
 

mmseg/core/evaluation/metrics.py

@@ -7,7 +7,7 @@ import torch
 
 
 def f_score(precision, recall, beta=1):
-    """calcuate the f-score value.
+    """calculate the f-score value.
 
     Args:
         precision (float | torch.Tensor): The precision value.
@@ -40,7 +40,7 @@ def intersect_and_union(pred_label,
         ignore_index (int): Index that will be ignored in evaluation.
         label_map (dict): Mapping old labels to new labels. The parameter will
             work only when label is str. Default: dict().
-        reduce_zero_label (bool): Wether ignore zero label. The parameter will
+        reduce_zero_label (bool): Whether ignore zero label. The parameter will
             work only when label is str. Default: False.
 
      Returns:
@@ -102,7 +102,7 @@ def total_intersect_and_union(results,
         num_classes (int): Number of categories.
         ignore_index (int): Index that will be ignored in evaluation.
         label_map (dict): Mapping old labels to new labels. Default: dict().
-        reduce_zero_label (bool): Wether ignore zero label. Default: False.
+        reduce_zero_label (bool): Whether ignore zero label. Default: False.
 
      Returns:
          ndarray: The intersection of prediction and ground truth histogram
@@ -148,7 +148,7 @@ def mean_iou(results,
         nan_to_num (int, optional): If specified, NaN values will be replaced
             by the numbers defined by the user. Default: None.
         label_map (dict): Mapping old labels to new labels. Default: dict().
-        reduce_zero_label (bool): Wether ignore zero label. Default: False.
+        reduce_zero_label (bool): Whether ignore zero label. Default: False.
 
      Returns:
         dict[str, float | ndarray]:
@@ -187,7 +187,7 @@ def mean_dice(results,
         nan_to_num (int, optional): If specified, NaN values will be replaced
             by the numbers defined by the user. Default: None.
         label_map (dict): Mapping old labels to new labels. Default: dict().
-        reduce_zero_label (bool): Wether ignore zero label. Default: False.
+        reduce_zero_label (bool): Whether ignore zero label. Default: False.
 
      Returns:
         dict[str, float | ndarray]: Default metrics.
@@ -228,7 +228,7 @@ def mean_fscore(results,
         nan_to_num (int, optional): If specified, NaN values will be replaced
             by the numbers defined by the user. Default: None.
         label_map (dict): Mapping old labels to new labels. Default: dict().
-        reduce_zero_label (bool): Wether ignore zero label. Default: False.
+        reduce_zero_label (bool): Whether ignore zero label. Default: False.
         beta (int): Determines the weight of recall in the combined score.
             Default: False.
 
@@ -274,7 +274,7 @@ def eval_metrics(results,
         nan_to_num (int, optional): If specified, NaN values will be replaced
             by the numbers defined by the user. Default: None.
         label_map (dict): Mapping old labels to new labels. Default: dict().
-        reduce_zero_label (bool): Wether ignore zero label. Default: False.
+        reduce_zero_label (bool): Whether ignore zero label. Default: False.
      Returns:
         float: Overall accuracy on all images.
         ndarray: Per category accuracy, shape (num_classes, ).

mmseg/datasets/pipelines/__init__.py

@@ -1,6 +1,6 @@
 # Copyright (c) OpenMMLab. All rights reserved.
 from .compose import Compose
-from .formating import (Collect, ImageToTensor, ToDataContainer, ToTensor,
+from .formatting import (Collect, ImageToTensor, ToDataContainer, ToTensor,
                          Transpose, to_tensor)
 from .loading import LoadAnnotations, LoadImageFromFile
 from .test_time_aug import MultiScaleFlipAug

mmseg/datasets/pipelines/formating.py

@@ -1,289 +1,9 @@
 # Copyright (c) OpenMMLab. All rights reserved.
-from collections.abc import Sequence
+# flake8: noqa
+import warnings
 
-import mmcv
+from .formatting import *
-import numpy as np
-import torch
-from mmcv.parallel import DataContainer as DC
 
-from ..builder import PIPELINES
+warnings.warn('DeprecationWarning: mmseg.datasets.pipelines.formating will be '
-
+              'deprecated in 2021, please replace it with '
-
+              'mmseg.datasets.pipelines.formatting.')
-def to_tensor(data):
-    """Convert objects of various python types to :obj:`torch.Tensor`.
-
-    Supported types are: :class:`numpy.ndarray`, :class:`torch.Tensor`,
-    :class:`Sequence`, :class:`int` and :class:`float`.
-
-    Args:
-        data (torch.Tensor | numpy.ndarray | Sequence | int | float): Data to
-            be converted.
-    """
-
-    if isinstance(data, torch.Tensor):
-        return data
-    elif isinstance(data, np.ndarray):
-        return torch.from_numpy(data)
-    elif isinstance(data, Sequence) and not mmcv.is_str(data):
-        return torch.tensor(data)
-    elif isinstance(data, int):
-        return torch.LongTensor([data])
-    elif isinstance(data, float):
-        return torch.FloatTensor([data])
-    else:
-        raise TypeError(f'type {type(data)} cannot be converted to tensor.')
-
-
-@PIPELINES.register_module()
-class ToTensor(object):
-    """Convert some results to :obj:`torch.Tensor` by given keys.
-
-    Args:
-        keys (Sequence[str]): Keys that need to be converted to Tensor.
-    """
-
-    def __init__(self, keys):
-        self.keys = keys
-
-    def __call__(self, results):
-        """Call function to convert data in results to :obj:`torch.Tensor`.
-
-        Args:
-            results (dict): Result dict contains the data to convert.
-
-        Returns:
-            dict: The result dict contains the data converted
-                to :obj:`torch.Tensor`.
-        """
-
-        for key in self.keys:
-            results[key] = to_tensor(results[key])
-        return results
-
-    def __repr__(self):
-        return self.__class__.__name__ + f'(keys={self.keys})'
-
-
-@PIPELINES.register_module()
-class ImageToTensor(object):
-    """Convert image to :obj:`torch.Tensor` by given keys.
-
-    The dimension order of input image is (H, W, C). The pipeline will convert
-    it to (C, H, W). If only 2 dimension (H, W) is given, the output would be
-    (1, H, W).
-
-    Args:
-        keys (Sequence[str]): Key of images to be converted to Tensor.
-    """
-
-    def __init__(self, keys):
-        self.keys = keys
-
-    def __call__(self, results):
-        """Call function to convert image in results to :obj:`torch.Tensor` and
-        transpose the channel order.
-
-        Args:
-            results (dict): Result dict contains the image data to convert.
-
-        Returns:
-            dict: The result dict contains the image converted
-                to :obj:`torch.Tensor` and transposed to (C, H, W) order.
-        """
-
-        for key in self.keys:
-            img = results[key]
-            if len(img.shape) < 3:
-                img = np.expand_dims(img, -1)
-            results[key] = to_tensor(img.transpose(2, 0, 1))
-        return results
-
-    def __repr__(self):
-        return self.__class__.__name__ + f'(keys={self.keys})'
-
-
-@PIPELINES.register_module()
-class Transpose(object):
-    """Transpose some results by given keys.
-
-    Args:
-        keys (Sequence[str]): Keys of results to be transposed.
-        order (Sequence[int]): Order of transpose.
-    """
-
-    def __init__(self, keys, order):
-        self.keys = keys
-        self.order = order
-
-    def __call__(self, results):
-        """Call function to convert image in results to :obj:`torch.Tensor` and
-        transpose the channel order.
-
-        Args:
-            results (dict): Result dict contains the image data to convert.
-
-        Returns:
-            dict: The result dict contains the image converted
-                to :obj:`torch.Tensor` and transposed to (C, H, W) order.
-        """
-
-        for key in self.keys:
-            results[key] = results[key].transpose(self.order)
-        return results
-
-    def __repr__(self):
-        return self.__class__.__name__ + \
-               f'(keys={self.keys}, order={self.order})'
-
-
-@PIPELINES.register_module()
-class ToDataContainer(object):
-    """Convert results to :obj:`mmcv.DataContainer` by given fields.
-
-    Args:
-        fields (Sequence[dict]): Each field is a dict like
-            ``dict(key='xxx', **kwargs)``. The ``key`` in result will
-            be converted to :obj:`mmcv.DataContainer` with ``**kwargs``.
-            Default: ``(dict(key='img', stack=True),
-            dict(key='gt_semantic_seg'))``.
-    """
-
-    def __init__(self,
-                 fields=(dict(key='img',
-                              stack=True), dict(key='gt_semantic_seg'))):
-        self.fields = fields
-
-    def __call__(self, results):
-        """Call function to convert data in results to
-        :obj:`mmcv.DataContainer`.
-
-        Args:
-            results (dict): Result dict contains the data to convert.
-
-        Returns:
-            dict: The result dict contains the data converted to
-                :obj:`mmcv.DataContainer`.
-        """
-
-        for field in self.fields:
-            field = field.copy()
-            key = field.pop('key')
-            results[key] = DC(results[key], **field)
-        return results
-
-    def __repr__(self):
-        return self.__class__.__name__ + f'(fields={self.fields})'
-
-
-@PIPELINES.register_module()
-class DefaultFormatBundle(object):
-    """Default formatting bundle.
-
-    It simplifies the pipeline of formatting common fields, including "img"
-    and "gt_semantic_seg". These fields are formatted as follows.
-
-    - img: (1)transpose, (2)to tensor, (3)to DataContainer (stack=True)
-    - gt_semantic_seg: (1)unsqueeze dim-0 (2)to tensor,
-                       (3)to DataContainer (stack=True)
-    """
-
-    def __call__(self, results):
-        """Call function to transform and format common fields in results.
-
-        Args:
-            results (dict): Result dict contains the data to convert.
-
-        Returns:
-            dict: The result dict contains the data that is formatted with
-                default bundle.
-        """
-
-        if 'img' in results:
-            img = results['img']
-            if len(img.shape) < 3:
-                img = np.expand_dims(img, -1)
-            img = np.ascontiguousarray(img.transpose(2, 0, 1))
-            results['img'] = DC(to_tensor(img), stack=True)
-        if 'gt_semantic_seg' in results:
-            # convert to long
-            results['gt_semantic_seg'] = DC(
-                to_tensor(results['gt_semantic_seg'][None,
-                                                     ...].astype(np.int64)),
-                stack=True)
-        return results
-
-    def __repr__(self):
-        return self.__class__.__name__
-
-
-@PIPELINES.register_module()
-class Collect(object):
-    """Collect data from the loader relevant to the specific task.
-
-    This is usually the last stage of the data loader pipeline. Typically keys
-    is set to some subset of "img", "gt_semantic_seg".
-
-    The "img_meta" item is always populated.  The contents of the "img_meta"
-    dictionary depends on "meta_keys". By default this includes:
-
-        - "img_shape": shape of the image input to the network as a tuple
-            (h, w, c).  Note that images may be zero padded on the bottom/right
-            if the batch tensor is larger than this shape.
-
-        - "scale_factor": a float indicating the preprocessing scale
-
-        - "flip": a boolean indicating if image flip transform was used
-
-        - "filename": path to the image file
-
-        - "ori_shape": original shape of the image as a tuple (h, w, c)
-
-        - "pad_shape": image shape after padding
-
-        - "img_norm_cfg": a dict of normalization information:
-            - mean - per channel mean subtraction
-            - std - per channel std divisor
-            - to_rgb - bool indicating if bgr was converted to rgb
-
-    Args:
-        keys (Sequence[str]): Keys of results to be collected in ``data``.
-        meta_keys (Sequence[str], optional): Meta keys to be converted to
-            ``mmcv.DataContainer`` and collected in ``data[img_metas]``.
-            Default: (``filename``, ``ori_filename``, ``ori_shape``,
-            ``img_shape``, ``pad_shape``, ``scale_factor``, ``flip``,
-            ``flip_direction``, ``img_norm_cfg``)
-    """
-
-    def __init__(self,
-                 keys,
-                 meta_keys=('filename', 'ori_filename', 'ori_shape',
-                            'img_shape', 'pad_shape', 'scale_factor', 'flip',
-                            'flip_direction', 'img_norm_cfg')):
-        self.keys = keys
-        self.meta_keys = meta_keys
-
-    def __call__(self, results):
-        """Call function to collect keys in results. The keys in ``meta_keys``
-        will be converted to :obj:mmcv.DataContainer.
-
-        Args:
-            results (dict): Result dict contains the data to collect.
-
-        Returns:
-            dict: The result dict contains the following keys
-                - keys in``self.keys``
-                - ``img_metas``
-        """
-
-        data = {}
-        img_meta = {}
-        for key in self.meta_keys:
-            img_meta[key] = results[key]
-        data['img_metas'] = DC(img_meta, cpu_only=True)
-        for key in self.keys:
-            data[key] = results[key]
-        return data
-
-    def __repr__(self):
-        return self.__class__.__name__ + \
-               f'(keys={self.keys}, meta_keys={self.meta_keys})'

mmseg/datasets/pipelines/formatting.py

@@ -0,0 +1,289 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+from collections.abc import Sequence
+
+import mmcv
+import numpy as np
+import torch
+from mmcv.parallel import DataContainer as DC
+
+from ..builder import PIPELINES
+
+
+def to_tensor(data):
+    """Convert objects of various python types to :obj:`torch.Tensor`.
+
+    Supported types are: :class:`numpy.ndarray`, :class:`torch.Tensor`,
+    :class:`Sequence`, :class:`int` and :class:`float`.
+
+    Args:
+        data (torch.Tensor | numpy.ndarray | Sequence | int | float): Data to
+            be converted.
+    """
+
+    if isinstance(data, torch.Tensor):
+        return data
+    elif isinstance(data, np.ndarray):
+        return torch.from_numpy(data)
+    elif isinstance(data, Sequence) and not mmcv.is_str(data):
+        return torch.tensor(data)
+    elif isinstance(data, int):
+        return torch.LongTensor([data])
+    elif isinstance(data, float):
+        return torch.FloatTensor([data])
+    else:
+        raise TypeError(f'type {type(data)} cannot be converted to tensor.')
+
+
+@PIPELINES.register_module()
+class ToTensor(object):
+    """Convert some results to :obj:`torch.Tensor` by given keys.
+
+    Args:
+        keys (Sequence[str]): Keys that need to be converted to Tensor.
+    """
+
+    def __init__(self, keys):
+        self.keys = keys
+
+    def __call__(self, results):
+        """Call function to convert data in results to :obj:`torch.Tensor`.
+
+        Args:
+            results (dict): Result dict contains the data to convert.
+
+        Returns:
+            dict: The result dict contains the data converted
+                to :obj:`torch.Tensor`.
+        """
+
+        for key in self.keys:
+            results[key] = to_tensor(results[key])
+        return results
+
+    def __repr__(self):
+        return self.__class__.__name__ + f'(keys={self.keys})'
+
+
+@PIPELINES.register_module()
+class ImageToTensor(object):
+    """Convert image to :obj:`torch.Tensor` by given keys.
+
+    The dimension order of input image is (H, W, C). The pipeline will convert
+    it to (C, H, W). If only 2 dimension (H, W) is given, the output would be
+    (1, H, W).
+
+    Args:
+        keys (Sequence[str]): Key of images to be converted to Tensor.
+    """
+
+    def __init__(self, keys):
+        self.keys = keys
+
+    def __call__(self, results):
+        """Call function to convert image in results to :obj:`torch.Tensor` and
+        transpose the channel order.
+
+        Args:
+            results (dict): Result dict contains the image data to convert.
+
+        Returns:
+            dict: The result dict contains the image converted
+                to :obj:`torch.Tensor` and transposed to (C, H, W) order.
+        """
+
+        for key in self.keys:
+            img = results[key]
+            if len(img.shape) < 3:
+                img = np.expand_dims(img, -1)
+            results[key] = to_tensor(img.transpose(2, 0, 1))
+        return results
+
+    def __repr__(self):
+        return self.__class__.__name__ + f'(keys={self.keys})'
+
+
+@PIPELINES.register_module()
+class Transpose(object):
+    """Transpose some results by given keys.
+
+    Args:
+        keys (Sequence[str]): Keys of results to be transposed.
+        order (Sequence[int]): Order of transpose.
+    """
+
+    def __init__(self, keys, order):
+        self.keys = keys
+        self.order = order
+
+    def __call__(self, results):
+        """Call function to convert image in results to :obj:`torch.Tensor` and
+        transpose the channel order.
+
+        Args:
+            results (dict): Result dict contains the image data to convert.
+
+        Returns:
+            dict: The result dict contains the image converted
+                to :obj:`torch.Tensor` and transposed to (C, H, W) order.
+        """
+
+        for key in self.keys:
+            results[key] = results[key].transpose(self.order)
+        return results
+
+    def __repr__(self):
+        return self.__class__.__name__ + \
+               f'(keys={self.keys}, order={self.order})'
+
+
+@PIPELINES.register_module()
+class ToDataContainer(object):
+    """Convert results to :obj:`mmcv.DataContainer` by given fields.
+
+    Args:
+        fields (Sequence[dict]): Each field is a dict like
+            ``dict(key='xxx', **kwargs)``. The ``key`` in result will
+            be converted to :obj:`mmcv.DataContainer` with ``**kwargs``.
+            Default: ``(dict(key='img', stack=True),
+            dict(key='gt_semantic_seg'))``.
+    """
+
+    def __init__(self,
+                 fields=(dict(key='img',
+                              stack=True), dict(key='gt_semantic_seg'))):
+        self.fields = fields
+
+    def __call__(self, results):
+        """Call function to convert data in results to
+        :obj:`mmcv.DataContainer`.
+
+        Args:
+            results (dict): Result dict contains the data to convert.
+
+        Returns:
+            dict: The result dict contains the data converted to
+                :obj:`mmcv.DataContainer`.
+        """
+
+        for field in self.fields:
+            field = field.copy()
+            key = field.pop('key')
+            results[key] = DC(results[key], **field)
+        return results
+
+    def __repr__(self):
+        return self.__class__.__name__ + f'(fields={self.fields})'
+
+
+@PIPELINES.register_module()
+class DefaultFormatBundle(object):
+    """Default formatting bundle.
+
+    It simplifies the pipeline of formatting common fields, including "img"
+    and "gt_semantic_seg". These fields are formatted as follows.
+
+    - img: (1)transpose, (2)to tensor, (3)to DataContainer (stack=True)
+    - gt_semantic_seg: (1)unsqueeze dim-0 (2)to tensor,
+                       (3)to DataContainer (stack=True)
+    """
+
+    def __call__(self, results):
+        """Call function to transform and format common fields in results.
+
+        Args:
+            results (dict): Result dict contains the data to convert.
+
+        Returns:
+            dict: The result dict contains the data that is formatted with
+                default bundle.
+        """
+
+        if 'img' in results:
+            img = results['img']
+            if len(img.shape) < 3:
+                img = np.expand_dims(img, -1)
+            img = np.ascontiguousarray(img.transpose(2, 0, 1))
+            results['img'] = DC(to_tensor(img), stack=True)
+        if 'gt_semantic_seg' in results:
+            # convert to long
+            results['gt_semantic_seg'] = DC(
+                to_tensor(results['gt_semantic_seg'][None,
+                                                     ...].astype(np.int64)),
+                stack=True)
+        return results
+
+    def __repr__(self):
+        return self.__class__.__name__
+
+
+@PIPELINES.register_module()
+class Collect(object):
+    """Collect data from the loader relevant to the specific task.
+
+    This is usually the last stage of the data loader pipeline. Typically keys
+    is set to some subset of "img", "gt_semantic_seg".
+
+    The "img_meta" item is always populated.  The contents of the "img_meta"
+    dictionary depends on "meta_keys". By default this includes:
+
+        - "img_shape": shape of the image input to the network as a tuple
+            (h, w, c).  Note that images may be zero padded on the bottom/right
+            if the batch tensor is larger than this shape.
+
+        - "scale_factor": a float indicating the preprocessing scale
+
+        - "flip": a boolean indicating if image flip transform was used
+
+        - "filename": path to the image file
+
+        - "ori_shape": original shape of the image as a tuple (h, w, c)
+
+        - "pad_shape": image shape after padding
+
+        - "img_norm_cfg": a dict of normalization information:
+            - mean - per channel mean subtraction
+            - std - per channel std divisor
+            - to_rgb - bool indicating if bgr was converted to rgb
+
+    Args:
+        keys (Sequence[str]): Keys of results to be collected in ``data``.
+        meta_keys (Sequence[str], optional): Meta keys to be converted to
+            ``mmcv.DataContainer`` and collected in ``data[img_metas]``.
+            Default: (``filename``, ``ori_filename``, ``ori_shape``,
+            ``img_shape``, ``pad_shape``, ``scale_factor``, ``flip``,
+            ``flip_direction``, ``img_norm_cfg``)
+    """
+
+    def __init__(self,
+                 keys,
+                 meta_keys=('filename', 'ori_filename', 'ori_shape',
+                            'img_shape', 'pad_shape', 'scale_factor', 'flip',
+                            'flip_direction', 'img_norm_cfg')):
+        self.keys = keys
+        self.meta_keys = meta_keys
+
+    def __call__(self, results):
+        """Call function to collect keys in results. The keys in ``meta_keys``
+        will be converted to :obj:mmcv.DataContainer.
+
+        Args:
+            results (dict): Result dict contains the data to collect.
+
+        Returns:
+            dict: The result dict contains the following keys
+                - keys in``self.keys``
+                - ``img_metas``
+        """
+
+        data = {}
+        img_meta = {}
+        for key in self.meta_keys:
+            img_meta[key] = results[key]
+        data['img_metas'] = DC(img_meta, cpu_only=True)
+        for key in self.keys:
+            data[key] = results[key]
+        return data
+
+    def __repr__(self):
+        return self.__class__.__name__ + \
+               f'(keys={self.keys}, meta_keys={self.meta_keys})'

mmseg/models/backbones/bisenetv2.py

@@ -194,7 +194,7 @@ class GELayer(BaseModule):
         init_cfg (dict or list[dict], optional): Initialization config dict.
             Default: None.
     Returns:
-        x (torch.Tensor): Intermidiate feature map in
+        x (torch.Tensor): Intermediate feature map in
             Semantic Branch.
     """
 

mmseg/models/backbones/mit.py

@@ -186,7 +186,7 @@ class TransformerEncoderLayer(BaseModule):
         qkv_bias (bool): enable bias for qkv if True.
             Default: True.
         act_cfg (dict): The activation config for FFNs.
-            Defalut: dict(type='GELU').
+            Default: dict(type='GELU').
         norm_cfg (dict): Config dict for normalization layer.
             Default: dict(type='LN').
         batch_first (bool): Key, Query and Value are shape of
@@ -277,7 +277,7 @@ class MixVisionTransformer(BaseModule):
         norm_cfg (dict): Config dict for normalization layer.
             Default: dict(type='LN')
         act_cfg (dict): The activation config for FFNs.
-            Defalut: dict(type='GELU').
+            Default: dict(type='GELU').
         pretrained (str, optional): model pretrained path. Default: None.
         init_cfg (dict or list[dict], optional): Initialization config dict.
             Default: None.

mmseg/models/backbones/vit.py

@@ -33,7 +33,7 @@ class TransformerEncoderLayer(BaseModule):
             Default: 2.
         qkv_bias (bool): enable bias for qkv if True. Default: True
         act_cfg (dict): The activation config for FFNs.
-            Defalut: dict(type='GELU').
+            Default: dict(type='GELU').
         norm_cfg (dict): Config dict for normalization layer.
             Default: dict(type='LN').
         batch_first (bool): Key, Query and Value are shape of
@@ -126,7 +126,7 @@ class VisionTransformer(BaseModule):
         norm_cfg (dict): Config dict for normalization layer.
             Default: dict(type='LN')
         act_cfg (dict): The activation config for FFNs.
-            Defalut: dict(type='GELU').
+            Default: dict(type='GELU').
         patch_norm (bool): Whether to add a norm in PatchEmbed Block.
             Default: False.
         final_norm (bool): Whether to add a additional layer to normalize

mmseg/models/decode_heads/dpt_head.py

@@ -227,7 +227,7 @@ class DPTHead(BaseDecodeHead):
         expand_channels (bool): Whether expand the channels in post process
             block. Default: False.
         act_cfg (dict): The activation config for residual conv unit.
-            Defalut dict(type='ReLU').
+            Default dict(type='ReLU').
         norm_cfg (dict): Config dict for normalization layer.
             Default: dict(type='BN').
     """

mmseg/models/losses/utils.py

@@ -51,7 +51,7 @@ def weight_reduce_loss(loss, weight=None, reduction='mean', avg_factor=None):
         loss (Tensor): Element-wise loss.
         weight (Tensor): Element-wise weights.
         reduction (str): Same as built-in losses of PyTorch.
-        avg_factor (float): Avarage factor when computing the mean of losses.
+        avg_factor (float): Average factor when computing the mean of losses.
 
     Returns:
         Tensor: Processed loss values.

mmseg/models/utils/shape_convert.py

@@ -3,11 +3,11 @@ def nlc_to_nchw(x, hw_shape):
     """Convert [N, L, C] shape tensor to [N, C, H, W] shape tensor.
 
     Args:
-        x (Tensor): The input tensor of shape [N, L, C] before convertion.
+        x (Tensor): The input tensor of shape [N, L, C] before conversion.
         hw_shape (Sequence[int]): The height and width of output feature map.
 
     Returns:
-        Tensor: The output tensor of shape [N, C, H, W] after convertion.
+        Tensor: The output tensor of shape [N, C, H, W] after conversion.
     """
     H, W = hw_shape
     assert len(x.shape) == 3
@@ -20,10 +20,10 @@ def nchw_to_nlc(x):
     """Flatten [N, C, H, W] shape tensor to [N, L, C] shape tensor.
 
     Args:
-        x (Tensor): The input tensor of shape [N, C, H, W] before convertion.
+        x (Tensor): The input tensor of shape [N, C, H, W] before conversion.
 
     Returns:
-        Tensor: The output tensor of shape [N, L, C] after convertion.
+        Tensor: The output tensor of shape [N, L, C] after conversion.
     """
     assert len(x.shape) == 4
     return x.flatten(2).transpose(1, 2).contiguous()

setup.cfg

@@ -11,3 +11,9 @@ known_first_party = mmseg
 known_third_party = PIL,cityscapesscripts,cv2,detail,matplotlib,mmcv,numpy,onnxruntime,packaging,prettytable,pytest,pytorch_sphinx_theme,requests,scipy,seaborn,torch,ts
 no_lines_before = STDLIB,LOCALFOLDER
 default_section = THIRDPARTY
+
+[codespell]
+skip = *.po,*.ts,*.ipynb
+count =
+quiet-level = 3
+ignore-words-list = formating,sur,hist

tests/test_models/test_backbones/test_unet.py

@@ -425,7 +425,7 @@ def test_unet():
         unet(x)
 
     with pytest.raises(AssertionError):
-        # Check if num_stages matchs strides, len(strides)=num_stages
+        # Check if num_stages matches strides, len(strides)=num_stages
         unet = UNet(
             in_channels=3,
             base_channels=4,
@@ -440,7 +440,7 @@ def test_unet():
         unet(x)
 
     with pytest.raises(AssertionError):
-        # Check if num_stages matchs strides, len(enc_num_convs)=num_stages
+        # Check if num_stages matches strides, len(enc_num_convs)=num_stages
         unet = UNet(
             in_channels=3,
             base_channels=4,
@@ -455,7 +455,7 @@ def test_unet():
         unet(x)
 
     with pytest.raises(AssertionError):
-        # Check if num_stages matchs strides, len(dec_num_convs)=num_stages-1
+        # Check if num_stages matches strides, len(dec_num_convs)=num_stages-1
         unet = UNet(
             in_channels=3,
             base_channels=4,
@@ -470,7 +470,7 @@ def test_unet():
         unet(x)
 
     with pytest.raises(AssertionError):
-        # Check if num_stages matchs strides, len(downsamples)=num_stages-1
+        # Check if num_stages matches strides, len(downsamples)=num_stages-1
         unet = UNet(
             in_channels=3,
             base_channels=4,
@@ -485,7 +485,7 @@ def test_unet():
         unet(x)
 
     with pytest.raises(AssertionError):
-        # Check if num_stages matchs strides, len(enc_dilations)=num_stages
+        # Check if num_stages matches strides, len(enc_dilations)=num_stages
         unet = UNet(
             in_channels=3,
             base_channels=4,
@@ -500,7 +500,7 @@ def test_unet():
         unet(x)
 
     with pytest.raises(AssertionError):
-        # Check if num_stages matchs strides, len(dec_dilations)=num_stages-1
+        # Check if num_stages matches strides, len(dec_dilations)=num_stages-1
         unet = UNet(
             in_channels=3,
             base_channels=4,

tests/test_models/test_utils/test_embed.py

@@ -173,7 +173,7 @@ def test_patch_embed():
     # test L = out_h * out_w
     assert shape[0] * shape[1] == x3.shape[1]
 
-    # test thte init_out_size with nn.Unfold
+    # test the init_out_size with nn.Unfold
     assert patch_merge_3.init_out_size[1] == (input_size[0] - 2 * 4 -
                                               1) // 2 + 1
     assert patch_merge_3.init_out_size[0] == (input_size[0] - 2 * 4 -
@@ -195,7 +195,7 @@ def test_patch_embed():
 
     _, shape = patch_merge_3(dummy_input)
     # when input_size equal to real input
-    # the out_size shoule be equal to `init_out_size`
+    # the out_size should be equal to `init_out_size`
     assert shape == patch_merge_3.init_out_size
 
     input_size = (H, W)
@@ -213,7 +213,7 @@ def test_patch_embed():
 
     _, shape = patch_merge_3(dummy_input)
     # when input_size equal to real input
-    # the out_size shoule be equal to `init_out_size`
+    # the out_size should be equal to `init_out_size`
     assert shape == patch_merge_3.init_out_size
 
     # test adap padding
@@ -288,7 +288,7 @@ def test_patch_embed():
         assert out_size == (2, 1)
         assert x_out.size(1) == out_size[0] * out_size[1]
 
-        # test different kernel_size with diffrent stride
+        # test different kernel_size with different stride
         input_size = (6, 5)
         kernel_size = (6, 2)
         stride = (6, 2)
@@ -437,7 +437,7 @@ def test_patch_merging():
         assert out_size == (2, 1)
         assert x_out.size(1) == out_size[0] * out_size[1]
 
-        # test different kernel_size with diffrent stride
+        # test different kernel_size with different stride
         input_size = (6, 5)
         kernel_size = (6, 2)
         stride = (6, 2)

tools/model_converters/mit2mmseg.py

@@ -14,14 +14,14 @@ def convert_mit(ckpt):
     for k, v in ckpt.items():
         if k.startswith('head'):
             continue
-        # patch embedding convertion
+        # patch embedding conversion
         elif k.startswith('patch_embed'):
             stage_i = int(k.split('.')[0].replace('patch_embed', ''))
             new_k = k.replace(f'patch_embed{stage_i}', f'layers.{stage_i-1}.0')
             new_v = v
             if 'proj.' in new_k:
                 new_k = new_k.replace('proj.', 'projection.')
-        # transformer encoder layer convertion
+        # transformer encoder layer conversion
         elif k.startswith('block'):
             stage_i = int(k.split('.')[0].replace('block', ''))
             new_k = k.replace(f'block{stage_i}', f'layers.{stage_i-1}.1')
@@ -45,7 +45,7 @@ def convert_mit(ckpt):
                 new_k = new_k.replace('dwconv.dwconv.', '1.')
                 new_k = new_k.replace('fc2.', '4.')
                 string += f'{new_k} {v.shape}-{new_v.shape}'
-        # norm layer convertion
+        # norm layer conversion
         elif k.startswith('norm'):
             stage_i = int(k.split('.')[0].replace('norm', ''))
             new_k = k.replace(f'norm{stage_i}', f'layers.{stage_i-1}.2')

tools/onnx2tensorrt.py

@@ -117,7 +117,7 @@ def onnx2tensorrt(onnx_file: str,
     import tensorrt as trt
     min_shape = input_config['min_shape']
     max_shape = input_config['max_shape']
-    # create trt engine and wraper
+    # create trt engine and wrapper
     opt_shape_dict = {'input': [min_shape, min_shape, max_shape]}
     max_workspace_size = get_GiB(workspace_size)
     trt_engine = onnx2trt(
@@ -254,7 +254,7 @@ if __name__ == '__main__':
         'Dataset {} does not found.'.format(args.dataset)
     for max_value, min_value in zip(args.max_shape, args.min_shape):
         assert max_value >= min_value, \
-            'max_shape sould be larger than min shape'
+            'max_shape should be larger than min shape'
 
     input_config = {
         'min_shape': args.min_shape,

tools/pytorch2torchscript.py

@@ -113,7 +113,7 @@ def pytorch2libtorch(model,
 
     imgs = mm_inputs.pop('imgs')
 
-    # replace the orginal forword with forward_dummy
+    # replace the original forword with forward_dummy
     model.forward = model.forward_dummy
     model.eval()
     traced_model = torch.jit.trace(