This commit is contained in:
Xiangxu-0103 2022-03-23 10:36:27 +08:00 committed by GitHub
parent b0fd8ae68e
commit 98984bf855
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -16,8 +16,8 @@ class FPN(BaseModule):
Detection <https://arxiv.org/abs/1612.03144>`_.
Args:
in_channels (List[int]): Number of input channels per scale.
out_channels (int): Number of output channels (used at each scale)
in_channels (list[int]): Number of input channels per scale.
out_channels (int): Number of output channels (used at each scale).
num_outs (int): Number of output scales.
start_level (int): Index of the start input backbone level used to
build the feature pyramid. Default: 0.
@ -30,7 +30,7 @@ class FPN(BaseModule):
Only the following options are allowed
- 'on_input': Last feat map of neck inputs (i.e. backbone feature).
- 'on_lateral': Last feature map after lateral convs.
- 'on_lateral': Last feature map after lateral convs.
- 'on_output': The last output feature map after fpn convs.
extra_convs_on_inputs (bool, deprecated): Whether to apply extra convs
on the original feature from the backbone. If True,
@ -42,10 +42,10 @@ class FPN(BaseModule):
Default: False.
conv_cfg (dict): Config dict for convolution layer. Default: None.
norm_cfg (dict): Config dict for normalization layer. Default: None.
act_cfg (str): Config dict for activation layer in ConvModule.
act_cfg (dict): Config dict for activation layer in ConvModule.
Default: None.
upsample_cfg (dict): Config dict for interpolate layer.
Default: `dict(mode='nearest')`
Default: dict(mode='nearest').
init_cfg (dict or list[dict], optional): Initialization config dict.
Example: