fastreid.modeling.backbones.osnet.ChannelGate Class Reference

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

Public Member Functions
	__init__ (self, in_channels, num_gates=None, return_gates=False, gate_activation='sigmoid', reduction=16, layer_norm=False)
	forward (self, x)

Public Attributes
	return_gates
	global_avgpool
	fc1
	norm1
	relu
	fc2
	gate_activation

Detailed Description

A mini-network that generates channel-wise gates conditioned on input tensor.

Definition at line 171 of file osnet.py.

Constructor & Destructor Documentation

__init__()

fastreid.modeling.backbones.osnet.ChannelGate.__init__	(		self,
			in_channels,
			num_gates = None,
			return_gates = False,
			gate_activation = 'sigmoid',
			reduction = 16,
			layer_norm = False )

Definition at line 174 of file osnet.py.

    ):
        super(ChannelGate, self).__init__()
        if num_gates is None: num_gates = in_channels
        self.return_gates = return_gates
 
        self.global_avgpool = nn.AdaptiveAvgPool2d(1)
 
        self.fc1 = nn.Conv2d(
            in_channels,
            in_channels // reduction,
            kernel_size=1,
            bias=True,
            padding=0
        )
        self.norm1 = None
        if layer_norm: self.norm1 = nn.LayerNorm((in_channels // reduction, 1, 1))
        self.relu = nn.ReLU(inplace=True)
        self.fc2 = nn.Conv2d(
            in_channels // reduction,
            num_gates,
            kernel_size=1,
            bias=True,
            padding=0
        )
        if gate_activation == 'sigmoid':
            self.gate_activation = nn.Sigmoid()
        elif gate_activation == 'relu':
            self.gate_activation = nn.ReLU(inplace=True)
        elif gate_activation == 'linear':
            self.gate_activation = nn.Identity()
        else:
            raise RuntimeError(
                "Unknown gate activation: {}".format(gate_activation)
            )
 

Member Function Documentation

forward()

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

Definition at line 217 of file osnet.py.

    def forward(self, x):
        input = x
        x = self.global_avgpool(x)
        x = self.fc1(x)
        if self.norm1 is not None: x = self.norm1(x)
        x = self.relu(x)
        x = self.fc2(x)
        x = self.gate_activation(x)
        if self.return_gates: return x
        return input * x
 
 

Member Data Documentation

fc1

fastreid.modeling.backbones.osnet.ChannelGate.fc1

Definition at line 189 of file osnet.py.

fc2

fastreid.modeling.backbones.osnet.ChannelGate.fc2

Definition at line 199 of file osnet.py.

gate_activation

fastreid.modeling.backbones.osnet.ChannelGate.gate_activation

Definition at line 207 of file osnet.py.

global_avgpool

fastreid.modeling.backbones.osnet.ChannelGate.global_avgpool

Definition at line 187 of file osnet.py.

norm1

fastreid.modeling.backbones.osnet.ChannelGate.norm1

Definition at line 196 of file osnet.py.

relu

fastreid.modeling.backbones.osnet.ChannelGate.relu

Definition at line 198 of file osnet.py.

return_gates

fastreid.modeling.backbones.osnet.ChannelGate.return_gates

Definition at line 185 of file osnet.py.

---

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

• smreid/fastreid/modeling/backbones/osnet.py