BUG解決：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
首選說一下這個(gè)問題，這個(gè)問題提示想要得到的是464個(gè)通道數(shù)但是實(shí)際上得到的是116個(gè)通道。
例如我給某個(gè)深度學(xué)習(xí)網(wǎng)絡(luò)中加CBAM注意力集中機(jī)制，具體可參照此文章鏈接: link.（以下為實(shí)現(xiàn)代碼）：

# 通道注意力機(jī)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)

# 空間注意力機(jī)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)

問題出現(xiàn)的可能原因1：

 # 在網(wǎng)絡(luò)的某層加入CBAM注意力機(jī)制
 self.ca = ChannelAttention(self.inplanes)
 self.sa = SpatialAttention()

self.inplanes修改為你上一層輸出的通道數(shù)；
出現(xiàn)原因2：是我在假的過程中出現(xiàn)的錯(cuò)誤，是一個(gè)非常小的錯(cuò)誤，就是在初始層和末尾分別加入CBAM的時(shí)候，沒有區(qū)分不同位置加入后的函數(shù)名，因此出現(xiàn)錯(cuò)誤，例如如下：

 # 在網(wǎng)絡(luò)的第一層加入CBAM注意力機(jī)制
 self.ca = ChannelAttention(self.inplanes)
 self.sa = SpatialAttention()
 # 在網(wǎng)絡(luò)的最后層加入CBAM注意力機(jī)制
 self.ca1 = ChannelAttention(self.inplanes)
 self.sa1 = SpatialAttention()

哎?。。。⌒枰獏^(qū)分函數(shù)名；
出現(xiàn)原因3：如果不是在開始或者最后層加入的注意力機(jī)制，而是在網(wǎng)絡(luò)結(jié)構(gòu)中加入，例如可以在resnet中的殘差結(jié)構(gòu)中，加入后可print（model）看一看是不是和自己想的一樣，我出現(xiàn)的問題是我想在每個(gè)block中加入注意力集中機(jī)制，因此把加入的部分寫在的模型結(jié)構(gòu)的block中，結(jié)果也出現(xiàn)了2所出現(xiàn)的問題，原因還是和2一樣。

總結(jié)：其實(shí)加入注意力集中機(jī)制還是比較容易的，仔細(xì)再仔細(xì)，一定沒問題，共勉。

附集中注意力集中機(jī)制實(shí)現(xiàn)代碼（PYTORCH）：文章來源地址http://www.zghlxwxcb.cn/news/detail-402922.html

#SE
class 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注意力機(jī)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)

#CoorAttention
class 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) / 6


class 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

到了這里，關(guān)于RuntimeError: Given groups=1, weight of size [14, 464, 1, 1], expected input問題解決的文章就介紹完了。如果您還想了解更多內(nèi)容，請?jiān)谟疑辖撬阉鱐OY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！