[Docs] Fix some errors in `config.md` and `how_to.md` (#200)

* Update config.md

* Update docs/zh_cn/user_guides/config.md

Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>

* [Docs] Fix some error in how_to.md

* Update docs/zh_cn/advanced_guides/how_to.md

Co-authored-by: Range King <RangeKingHZ@gmail.com>

* Update docs/zh_cn/advanced_guides/how_to.md

Co-authored-by: Range King <RangeKingHZ@gmail.com>

* Update docs/zh_cn/advanced_guides/how_to.md

Co-authored-by: Range King <RangeKingHZ@gmail.com>

* Update docs/zh_cn/advanced_guides/how_to.md

Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

* Update yolov5_head.py

* Update yolox_head.py

* Update yolov5_head.py

* Update yolox_head.py

* Update docs/zh_cn/advanced_guides/how_to.md

Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>

* Update how_to.md

* Update yolov5_head.py

* Update yolox_head.py

Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com>
Co-authored-by: Range King <RangeKingHZ@gmail.com>
Co-authored-by: HinGwenWoong <peterhuang0323@qq.com>

docs/en/advanced_guides/how_to.md

@@ -30,6 +30,8 @@ If you want to stack multiple Necks, you can directly set the Neck parameters in
 ```python
 _base_ = './yolov5_s-v61_syncbn_8xb16-300e_coco.py'
 
+deepen_factor = _base_.deepen_factor
+widen_factor = _base_.widen_factor
 model = dict(
     type='YOLODetector',
     neck=[
@@ -38,7 +40,7 @@ model = dict(
             deepen_factor=deepen_factor,
             widen_factor=widen_factor,
             in_channels=[256, 512, 1024],
-            out_channels=[256, 512, 1024],
+            out_channels=[256, 512, 1024], # The out_channels is controlled by widen_factor，so the YOLOv5PAFPN's out_channels equls to out_channels * widen_factor
             num_csp_blocks=3,
             norm_cfg=dict(type='BN', momentum=0.03, eps=0.001),
             act_cfg=dict(type='SiLU', inplace=True)),
@@ -55,4 +57,6 @@ model = dict(
             # disable zero_init_offset to follow official implementation
             zero_init_offset=False)
     ]
+    bbox_head=dict(head_module=dict(in_channels=[512,512,512])) # The out_channels is controlled by widen_factor，so the YOLOv5HeadModuled in_channels * widen_factor equals to  the last neck's out_channels
+)
 ```

docs/zh_cn/advanced_guides/how_to.md

@@ -30,6 +30,8 @@ model = dict(
 ```python
 _base_ = './yolov5_s-v61_syncbn_8xb16-300e_coco.py'
 
+deepen_factor = _base_.deepen_factor
+widen_factor = _base_.widen_factor
 model = dict(
     type='YOLODetector',
     neck=[
@@ -38,7 +40,7 @@ model = dict(
             deepen_factor=deepen_factor,
             widen_factor=widen_factor,
             in_channels=[256, 512, 1024],
-            out_channels=[256, 512, 1024],
+            out_channels=[256, 512, 1024], # 因为 out_channels 由 widen_factor 控制，YOLOv5PAFPN 的 out_channels = out_channels * widen_factor
             num_csp_blocks=3,
             norm_cfg=dict(type='BN', momentum=0.03, eps=0.001),
             act_cfg=dict(type='SiLU', inplace=True)),
@@ -55,4 +57,6 @@ model = dict(
             # disable zero_init_offset to follow official implementation
             zero_init_offset=False)
     ]
+    bbox_head=dict(head_module=dict(in_channels=[512,512,512])) # 因为 out_channels 由 widen_factor 控制，YOLOv5HeadModuled 的 in_channels * widen_factor 才会等于最后一个 neck 的 out_channels
+)
 ```

docs/zh_cn/user_guides/config.md

@@ -529,7 +529,7 @@ pre_transform = _base_.pre_transform # 变量 pre_transform 等于 _base_ 中定
 
 - 更新配置列表中的键
 
-  在配置文件里，一些字典型的配置被包含在列表中。例如，数据训练流程 `data.train.pipeline` 通常是一个列表，比如 `[dict(type='LoadImageFromFile'), ...]`。如果需要将 `'LoadImageFromFile'` 改成 `'LoadImageFromWebcam'`，需要写成下述形式：`--cfg-options data.train.pipeline.0.type=LoadImageFromNDArray`.
+  在配置文件里，一些字典型的配置被包含在列表中。例如，数据训练流程 `data.train.pipeline` 通常是一个列表，比如 `[dict(type='LoadImageFromFile'), ...]`。如果需要将 `'LoadImageFromFile'` 改成 `'LoadImageFromNDArray'`，需要写成下述形式：`--cfg-options data.train.pipeline.0.type=LoadImageFromNDArray`.
 
 - 更新列表或元组的值
 

mmyolo/models/dense_heads/yolov5_head.py

@@ -27,7 +27,8 @@ class YOLOv5HeadModule(BaseModule):
     Args:
         num_classes (int): Number of categories excluding the background
             category.
-        in_channels (int): Number of channels in the input feature map.
+        in_channels (Union[int, Sequence]): Number of channels in the input
+            feature map.
         widen_factor (float): Width multiplier, multiply number of
             channels in each layer by this amount. Default: 1.0.
         num_base_priors:int: The number of priors (points) at a point

mmyolo/models/dense_heads/yolox_head.py

@@ -27,7 +27,8 @@ class YOLOXHeadModule(BaseModule):
     Args:
         num_classes (int): Number of categories excluding the background
             category.
-        in_channels (int): Number of channels in the input feature map.
+        in_channels (Union[int, Sequence]): Number of channels in the input
+            feature map.
         widen_factor (float): Width multiplier, multiply number of
             channels in each layer by this amount. Default: 1.0.
         num_base_priors (int): The number of priors (points) at a point