RuntimeError: Given groups=1, weight of size [14, 464, 1, 1], expected input问题解决

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_outreturn 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 1self.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）：

#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注意力机制
class eca_layer(nn.Module):"""Constructs a ECA module.Args:channel: Number of channels of the input feature mapk_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 informationy = self.avg_pool(x)# Two different branches of ECA moduley = self.conv(y.squeeze(-1).transpose(-1, -2)).transpose(-1, -2).unsqueeze(-1)# Multi-scale information fusiony = 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) / 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 = xn, 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_hreturn out

RuntimeError: Given groups=1, weight of size [14, 464, 1, 1], expected input问题解决相关推荐

RuntimeError: Given groups=1, weight of size [1, 1, 3, 3], expected input[1, 3, 1402, 1200] to have
RuntimeError: Given groups=1, weight of size [1, 1, 3, 3], expected input[1, 3, 1402, 1200] to have ...
(36)RuntimeError: Given groups=4, weight of size [4, 1, 11, 11], expected input xxxxxxxxx
问题描述: 在测试AODNet去雾网络时,计算测试集的指标ssim和psnr,从test_loader中读取测试集的清晰图像和去雾之后的图像,作为ssim的输入进行计算,原文代码如下: for ite ...
Pytorch RuntimeERROR: Given groups=1 weights of size [256,64,1,1] expected input[1,16,256,256] to
错误 Pytorch RuntimeERROR: Given groups=1 weights of size [256,64,1,1] expected input[1,16,256,256] to ...
BUG解决：RuntimeError:Given groups=1,weight of size...expected input...but got 3 channels instead.
https://www.codeleading.com/article/31383072717/
成功解决IndexError: index 14 is out of bounds for axis 1 with size 14
成功解决IndexError: index 14 is out of bounds for axis 1 with size 14 目录解决问题解决思路解决方法解决问题 IndexError: ...
[pcl::VoxelGrid::applyFilter] Leaf size is too small for the input dataset. Integer indices would ov
1. 报错日志: Python-pcl 点云下采样时报错如下: [pcl::VoxelGrid::applyFilter] Leaf size is too small for the input d ...
【Python】解决CNN中训练权重参数不匹配size mismatch for fc.weight，size mismatch for fc.bias
目录 1.问题描述 2.问题原因 3.问题解决 3.1思路1--忽视最后一层权重额外说明:假如载入权重不写strict=False, 直接是model.load_state_dict(pre_wei ...
RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED，以及tensorflow1.14.0+torch1.2.0+CUDA10.0配置
环境: Anaconda3-5.2.0 python3.6.5 初始tensorflow版本是1.8.0,cuda9.0,升级tensorflow至1.10.0时,出现torch1.1.0的运行错误: ...
ubuntu 14.04 使用apt-get出现如下问题解决办法
Some packages could not be installed. This may mean that you have requested an impossible situation ...

RuntimeError: Given groups=1, weight of size [14, 464, 1, 1], expected input问题解决

RuntimeError: Given groups=1, weight of size [14, 464, 1, 1], expected input问题解决相关推荐

最新文章

热门文章