Inheritance diagram for fastreid.layers.splat.SplAtConv2d:
Public Member Functions | |
| __init__ (self, in_channels, channels, kernel_size, stride=(1, 1), padding=(0, 0), dilation=(1, 1), groups=1, bias=True, radix=2, reduction_factor=4, rectify=False, rectify_avg=False, norm_layer=None, num_splits=1, dropblock_prob=0.0, **kwargs) | |
| forward (self, x) | |
Public Attributes | |
| rectify | |
| rectify_avg | |
| radix | |
| cardinality | |
| channels | |
| dropblock_prob | |
| conv | |
| use_bn | |
| bn0 | |
| relu | |
| fc1 | |
| bn1 | |
| fc2 | |
| rsoftmax | |
Detailed Description
Constructor & Destructor Documentation
◆ __init__()
| fastreid.layers.splat.SplAtConv2d.__init__ | ( | self, | |
| in_channels, | |||
| channels, | |||
| kernel_size, | |||
| stride = (1, 1), | |||
| padding = (0, 0), | |||
| dilation = (1, 1), | |||
| groups = 1, | |||
| bias = True, | |||
| radix = 2, | |||
| reduction_factor = 4, | |||
| rectify = False, | |||
| rectify_avg = False, | |||
| norm_layer = None, | |||
| num_splits = 1, | |||
| dropblock_prob = 0.0, | |||
| ** | kwargs ) |
Definition at line 19 of file splat.py.
23 dropblock_prob=0.0, **kwargs):
24 super(SplAtConv2d, self).__init__()
25 padding = _pair(padding)
26 self.rectify = rectify and (padding[0] > 0 or padding[1] > 0)
27 self.rectify_avg = rectify_avg
28 inter_channels = max(in_channels * radix // reduction_factor, 32)
29 self.radix = radix
30 self.cardinality = groups
31 self.channels = channels
32 self.dropblock_prob = dropblock_prob
33 if self.rectify:
34 from rfconv import RFConv2d
35 self.conv = RFConv2d(in_channels, channels * radix, kernel_size, stride, padding, dilation,
36 groups=groups * radix, bias=bias, average_mode=rectify_avg, **kwargs)
37 else:
38 self.conv = Conv2d(in_channels, channels * radix, kernel_size, stride, padding, dilation,
39 groups=groups * radix, bias=bias, **kwargs)
40 self.use_bn = norm_layer is not None
41 if self.use_bn:
42 self.bn0 = get_norm(norm_layer, channels * radix)
43 self.relu = ReLU(inplace=True)
44 self.fc1 = Conv2d(channels, inter_channels, 1, groups=self.cardinality)
45 if self.use_bn:
46 self.bn1 = get_norm(norm_layer, inter_channels)
47 self.fc2 = Conv2d(inter_channels, channels * radix, 1, groups=self.cardinality)
48
49 self.rsoftmax = rSoftMax(radix, groups)
50
Member Function Documentation
◆ forward()
| fastreid.layers.splat.SplAtConv2d.forward | ( | self, | |
| x ) |
Definition at line 51 of file splat.py.
51 def forward(self, x):
52 x = self.conv(x)
53 if self.use_bn:
54 x = self.bn0(x)
55 if self.dropblock_prob > 0.0:
56 x = self.dropblock(x)
57 x = self.relu(x)
58
59 batch, rchannel = x.shape[:2]
60 if self.radix > 1:
61 splited = torch.split(x, rchannel // self.radix, dim=1)
62 gap = sum(splited)
63 else:
64 gap = x
65 gap = F.adaptive_avg_pool2d(gap, 1)
66 gap = self.fc1(gap)
67
68 if self.use_bn:
69 gap = self.bn1(gap)
70 gap = self.relu(gap)
71
72 atten = self.fc2(gap)
73 atten = self.rsoftmax(atten).view(batch, -1, 1, 1)
74
75 if self.radix > 1:
76 attens = torch.split(atten, rchannel // self.radix, dim=1)
77 out = sum([att * split for (att, split) in zip(attens, splited)])
78 else:
79 out = atten * x
80 return out.contiguous()
81
82
Member Data Documentation
◆ bn0
◆ bn1
◆ cardinality
◆ channels
◆ conv
◆ dropblock_prob
◆ fc1
◆ fc2
◆ radix
◆ rectify
◆ rectify_avg
◆ relu
◆ rsoftmax
◆ use_bn
The documentation for this class was generated from the following file:
- smreid/fastreid/layers/splat.py
