Split-Attention Conv2d
| 17 | |
| 18 | |
| 19 | class SplAtConv2d(Module): |
| 20 | """Split-Attention Conv2d |
| 21 | """ |
| 22 | def __init__(self, in_channels, channels, kernel_size, stride=(1, 1), padding=(0, 0), |
| 23 | dilation=(1, 1), groups=1, bias=True, |
| 24 | radix=2, reduction_factor=4, |
| 25 | rectify=False, rectify_avg=False, norm_layer=None, |
| 26 | dropblock_prob=0.0, **kwargs): |
| 27 | super(SplAtConv2d, self).__init__() |
| 28 | padding = _pair(padding) |
| 29 | self.rectify = rectify and (padding[0] > 0 or padding[1] > 0) |
| 30 | self.rectify_avg = rectify_avg |
| 31 | inter_channels = max(in_channels*radix//reduction_factor, 32) |
| 32 | self.radix = radix |
| 33 | self.cardinality = groups |
| 34 | self.channels = channels |
| 35 | self.dropblock_prob = dropblock_prob |
| 36 | if self.rectify: |
| 37 | from rfconv import RFConv2d |
| 38 | self.conv = RFConv2d(in_channels, channels*radix, kernel_size, stride, padding, dilation, |
| 39 | groups=groups*radix, bias=bias, average_mode=rectify_avg, **kwargs) |
| 40 | else: |
| 41 | self.conv = Conv2d(in_channels, channels*radix, kernel_size, stride, padding, dilation, |
| 42 | groups=groups*radix, bias=bias, **kwargs) |
| 43 | self.use_bn = norm_layer is not None |
| 44 | self.bn0 = norm_layer(channels*radix) |
| 45 | self.relu = ReLU(inplace=True) |
| 46 | self.fc1 = Conv2d(channels, inter_channels, 1, groups=self.cardinality) |
| 47 | self.bn1 = norm_layer(inter_channels) |
| 48 | self.fc2 = Conv2d(inter_channels, channels*radix, 1, groups=self.cardinality) |
| 49 | if dropblock_prob > 0.0: |
| 50 | self.dropblock = DropBlock2D(dropblock_prob, 3) |
| 51 | |
| 52 | def forward(self, x): |
| 53 | x = self.conv(x) |
| 54 | if self.use_bn: |
| 55 | x = self.bn0(x) |
| 56 | if self.dropblock_prob > 0.0: |
| 57 | x = self.dropblock(x) |
| 58 | x = self.relu(x) |
| 59 | |
| 60 | batch, channel = x.shape[:2] |
| 61 | if self.radix > 1: |
| 62 | splited = torch.split(x, channel//self.radix, dim=1) |
| 63 | gap = sum(splited) |
| 64 | else: |
| 65 | gap = x |
| 66 | gap = F.adaptive_avg_pool2d(gap, 1) |
| 67 | gap = self.fc1(gap) |
| 68 | |
| 69 | if self.use_bn: |
| 70 | gap = self.bn1(gap) |
| 71 | gap = self.relu(gap) |
| 72 | |
| 73 | atten = self.fc2(gap).view((batch, self.radix, self.channels)) |
| 74 | if self.radix > 1: |
| 75 | atten = F.softmax(atten, dim=1).view(batch, -1, 1, 1) |
| 76 | else: |