mirrors/mmsegmentation
1
0
Fork 0
mirror of https://github.com/open-mmlab/mmsegmentation.git synced 2025-06-03 22:03:48 +08:00
Code Issues Projects Releases Wiki Activity

doc strings added

Browse Source
This commit is contained in:
johnzja 2020-08-07 15:15:13 +08:00
parent d3a53423c3
commit 2c77085dc2
2 changed files with 59 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
mmseg/models/backbones/fast_scnn.py
View File

@ -188,6 +188,44 @@ class FastSCNN(nn.Module):
norm_cfg=dict(type='BN'), norm_cfg=dict(type='BN'),
act_cfg=dict(type='ReLU'), act_cfg=dict(type='ReLU'),
align_corners=False): align_corners=False):
"""Fast-SCNN Backbone.
Args:
in_channels(int): Number of input image channels. Default=3 (RGB)
downsample_dw_channels1(int): Number of output channels after
the first conv layer in Learning-To-Downsample (LTD) module.
downsample_dw_channels2(int): Number of output channels after the second conv layer in LTD.
global_in_channels(int): Number of input channels of Global Feature Extractor(GFE).
Equal to number of output channels of LTD.
global_block_channels(tuple): Tuple of integers that describe the output channels for
each of the MobileNet-v2 bottleneck residual blocks in GFE.
global_out_channels(int): Number of output channels of GFE.
higher_in_channels(int): Number of input channels of the higher resolution branch in FFM.
Equal to global_in_channels.
lower_in_channels(int): Number of input channels of the lower resolution branch in FFM.
Equal to global_out_channels.
fusion_out_channels(int): Number of output channels of FFM.
scale_factor(int): The upsampling factor of the higher resolution branch in FFM.
Equal to the downsampling factor in GFE.
out_indices(tuple): Tuple of indices of list [higher_res_features, lower_res_features, fusion_output].
Often set to (0,1,2) to enable aux. heads.
conv_cfg (dict|None): Config of conv layers.
norm_cfg (dict|None): Config of norm layers.
act_cfg (dict): Config of activation layers.
align_corners (bool): align_corners argument of F.interpolate.
"""
super(FastSCNN, self).__init__() super(FastSCNN, self).__init__()
self.in_channels = in_channels self.in_channels = in_channels
self.downsample_dw_channels1 = downsample_dw_channels1 self.downsample_dw_channels1 = downsample_dw_channels1

21
mmseg/models/decode_heads/sep_fcn_head.py
View File

@ -5,6 +5,27 @@ from .fcn_head import FCNHead
@HEADS.register_module() @HEADS.register_module()
class SepFCNHead(FCNHead): class SepFCNHead(FCNHead):
"""Depthwise-Separable Fully Convolutional Network for Semantic Segmentation
This head is implemented according to Fast-SCNN.
Args:
in_channels(int): Number of output channels of FFM.
channels(int): Number of middle-stage channels in the decode head.
concat_input(bool): Whether to concatenate original decode input into
the result of consecutive convolution layers.
num_classes(int): Used to determine the dimension of final prediction tensor.
in_index(int): Correspond with 'out_indices' in FastSCNN backbone.
norm_cfg (dict|None): Config of norm layers.
align_corners (bool): align_corners argument of F.interpolate.
loss_decode(dict): Config of loss type and some relevant additional options.
"""
def __init__(self, **kwargs): def __init__(self, **kwargs):
super(SepFCNHead, self).__init__(**kwargs) super(SepFCNHead, self).__init__(**kwargs)