BUG解决:RuntimeError: Given groups=1, weight of size [14, 464, 1, 1], expected input[16, 116, 56, 1] to have 464 channels, but got 116 channels instead
首选说一下这个问题,这个问题提示想要得到的是464个通道数但是实际上得到的是116个通道。
例如我给某个深度学习网络中加CBAM注意力集中机制,具体可参照此文章链接: link.(以下为实现代码):
# 通道注意力机制class ChannelAttention(nn.Module): def __init__(self, in_planes, ratio=16): super(ChannelAttention, self).__init__() self.avg_pool = nn.AdaptiveAvgPool2d(1) self.max_pool = nn.AdaptiveMaxPool2d(1) self.fc1 = nn.Conv2d(in_planes, in_planes //ratio, 1, bias=False) self.relu1 = nn.ReLU() self.fc2 = nn.Conv2d(in_planes //ratio, in_planes, 1, bias=False) self.sigmoid = nn.Sigmoid() def forward(self, x): avg_out = self.fc2(self.relu1(self.fc1(self.avg_pool(x)))) max_out = self.fc2(self.relu1(self.fc1(self.max_pool(x)))) out = avg_out + max_out return self.sigmoid(out)# 空间注意力机制class SpatialAttention(nn.Module): def __init__(self, kernel_size=7): super(SpatialAttention, self).__init__() assert kernel_size in (3, 7), 'kernel size must be 3 or 7' padding = 3 if kernel_size == 7 else 1 self.conv1 = nn.Conv2d(2, 1, kernel_size, padding=padding, bias=False) self.sigmoid = nn.Sigmoid() def forward(self, x): avg_out = torch.mean(x, dim=1, keepdim=True) max_out, _ = torch.max(x, dim=1, keepdim=True) x = torch.cat([avg_out, max_out], dim=1) x = self.conv1(x) return self.sigmoid(x)
问题出现的可能原因1:
# 在网络的某层加入CBAM注意力机制 self.ca = ChannelAttention(self.inplanes) self.sa = SpatialAttention()
self.inplanes修改为你上一层输出的通道数;
出现原因2:是我在假的过程中出现的错误,是一个非常小的错误,就是在初始层和末尾分别加入CBAM的时候,没有区分不同位置加入后的函数名,因此出现错误,例如如下:
# 在网络的第一层加入CBAM注意力机制 self.ca = ChannelAttention(self.inplanes) self.sa = SpatialAttention() # 在网络的最后层加入CBAM注意力机制 self.ca1 = ChannelAttention(self.inplanes) self.sa1 = SpatialAttention()
哎!!!!需要区分函数名;
出现原因3:如果不是在开始或者最后层加入的注意力机制,而是在网络结构中加入,例如可以在resnet中的残差结构中,加入后可print(model)看一看是不是和自己想的一样,我出现的问题是我想在每个block中加入注意力集中机制,因此把加入的部分写在的模型结构的block中,结果也出现了2所出现的问题,原因还是和2一样。
总结:其实加入注意力集中机制还是比较容易的,仔细再仔细,一定没问题,共勉。
附集中注意力集中机制实现代码(PYTORCH):
#SEclass SELayer(nn.Module): def __init__(self, c1, r=16): super(SELayer, self).__init__() self.avgpool = nn.AdaptiveAvgPool2d(1) self.l1 = nn.Linear(c1, c1 // r, bias=False) self.relu = nn.ReLU(inplace=True) self.l2 = nn.Linear(c1 // r, c1, bias=False) self.sig = nn.Sigmoid() def forward(self, x): b, c, _, _ = x.size() y = self.avgpool(x).view(b, c) y = self.l1(y) y = self.relu(y) y = self.l2(y) y = self.sig(y) y = y.view(b, c, 1, 1) return x * y.expand_as(x)
# ECA注意力机制class eca_layer(nn.Module): """Constructs a ECA module. Args: channel: Number of channels of the input feature map k_size: Adaptive selection of kernel size """ def __init__(self, channel, k_size=3): super(eca_layer, self).__init__() self.avg_pool = nn.AdaptiveAvgPool2d(1) self.conv = nn.Conv1d(1, 1, kernel_size=k_size, padding=(k_size - 1) // 2, bias=False) self.sigmoid = nn.Sigmoid() def forward(self, x): # feature descriptor on the global spatial information y = self.avg_pool(x) # Two different branches of ECA module y = self.conv(y.squeeze(-1).transpose(-1, -2)).transpose(-1, -2).unsqueeze(-1) # Multi-scale information fusion y = self.sigmoid(y) x=x*y.expand_as(x) return x * y.expand_as(x)
#CoorAttentionclass h_sigmoid(nn.Module): def __init__(self, inplace=True): super(h_sigmoid, self).__init__() self.relu = nn.ReLU6(inplace=inplace) def forward(self, x): return self.relu(x + 3) / 6class h_swish(nn.Module): def __init__(self, inplace=True): super(h_swish, self).__init__() self.sigmoid = h_sigmoid(inplace=inplace) def forward(self, x): return x * self.sigmoid(x)class CoordAtt(nn.Module): def __init__(self, inp, oup, reduction=32): super(CoordAtt, self).__init__() self.pool_h = nn.AdaptiveAvgPool2d((None, 1)) self.pool_w = nn.AdaptiveAvgPool2d((1, None)) mip = max(8, inp // reduction) self.conv1 = nn.Conv2d(inp, mip, kernel_size=1, stride=1, padding=0) self.bn1 = nn.BatchNorm2d(mip) self.act = h_swish() self.conv_h = nn.Conv2d(mip, oup, kernel_size=1, stride=1, padding=0) self.conv_w = nn.Conv2d(mip, oup, kernel_size=1, stride=1, padding=0) def forward(self, x): identity = x n, c, h, w = x.size() x_h = self.pool_h(x) x_w = self.pool_w(x).permute(0, 1, 3, 2) y = torch.cat([x_h, x_w], dim=2) y = self.conv1(y) y = self.bn1(y) y = self.act(y) x_h, x_w = torch.split(y, [h, w], dim=2) x_w = x_w.permute(0, 1, 3, 2) a_h = self.conv_h(x_h).sigmoid() a_w = self.conv_w(x_w).sigmoid() out = identity * a_w * a_h return out