Inheritance diagram for fastreid.modeling.backbones.osnet.Conv1x1Linear:

Public Member Functions
	__init__ (self, in_channels, out_channels, bn_norm, stride=1)

	forward (self, x)

Public Attributes
	conv

	bn

Detailed Description

1x1 convolution + bn (w/o non-linearity).

Definition at line 98 of file osnet.py.

Constructor & Destructor Documentation

◆ init()

fastreid.modeling.backbones.osnet.Conv1x1Linear.__init__	(	self,
		in_channels,
		out_channels,
		bn_norm,
		stride = 1 )

Definition at line 101 of file osnet.py.

    def __init__(self, in_channels, out_channels, bn_norm, stride=1):
        super(Conv1x1Linear, self).__init__()
        self.conv = nn.Conv2d(
            in_channels, out_channels, 1, stride=stride, padding=0, bias=False
        )
        self.bn = get_norm(bn_norm, out_channels)
 

Member Function Documentation

◆ forward()

fastreid.modeling.backbones.osnet.Conv1x1Linear.forward	(		self,
			x )

Definition at line 108 of file osnet.py.

    def forward(self, x):
        x = self.conv(x)
        x = self.bn(x)
        return x
 
 

Member Data Documentation

◆ bn

fastreid.modeling.backbones.osnet.Conv1x1Linear.bn

Definition at line 106 of file osnet.py.

◆ conv

fastreid.modeling.backbones.osnet.Conv1x1Linear.conv

Definition at line 103 of file osnet.py.

The documentation for this class was generated from the following file:

smreid/fastreid/modeling/backbones/osnet.py

Public Member Functions

Public Attributes