為了處理視頻幀，我使用擠壓和激發塊來加權卷積層的通道。我想（使用torch.stack）將卷積層的通道（特征圖）與加權通道（通過使用提到的擠壓和激發塊）結合起來。但是我遇到了一個錯誤，當使用torch.stack(x, weighted_channels)與卷積層通道相關的引數時x，錯誤說TypeError: stack(): argument 'tensors' (position 1) must be tuple of Tensors, not Tensor.
class conv(nn.Module):
def __init__(self, in_channel, out_channel, out_sigmoid=False):
super(conv, self).__init__()
self.deconv = self._deconv(in_channel=512, out_channel=256, num_conv=3)
self.upsample = Upsample(scale_factor=2, mode='bilinear')
self.SEBlock = SE_Block(c=256)
def _deconv(self, in_channel, out_channel, num_conv=2, kernel_size=3, stride=1, padding=1):
layers=[]
layers.append(BasicConv2d(in_channel, out_channel,kernel_size=kernel_size, stride=stride, padding=padding))
for i in range(1, num_conv):
layers.append(_SepConv2d(out_channel, out_channel,kernel_size=kernel_size, stride=stride, padding=padding))
return nn.Sequential(*layers)
def forward(self, x):
x=self.deconv(x)
x = self.upsample(x)
stack = torch.stack(x, self.SEBlock(x,c=256))
return x
class BasicConv2d(nn.Module):
def __init__(self, in_planes, out_planes, kernel_size, stride, padding=0):
super(BasicConv2d, self).__init__()
self.conv = nn.Conv2d(in_planes, out_planes, kernel_size=kernel_size, stride=stride, padding=padding, bias=False)
self.bn = nn.BatchNorm2d(out_planes, eps=1e-3, momentum=0.001, affine=True)
self.relu = nn.ReLU()
def forward(self, x):
x = self.conv(x)
x = self.bn(x)
x = self.relu(x)
return x
class _SepConv2d(nn.Module):
def __init__(self, in_planes, out_planes, kernel_size, stride, padding=0):
super(_SepConv2d, self).__init__()
self.conv_s = nn.Conv2d(in_planes, out_planes, kernel_size=kernel_size, stride=stride, padding=padding, bias=False, groups=in_planes)
self.bn_s = nn.BatchNorm2d(out_planes)
self.relu_s = nn.ReLU()
self.conv_t = nn.Conv2d(out_planes, out_planes, kernel_size=1, stride=1, padding=0, bias=False)
self.bn_t = nn.BatchNorm2d(out_planes)
self.relu_t = nn.ReLU()
def forward(self, x):
x = self.conv_s(x)
x = self.bn_s(x)
x = self.relu_s(x)
x = self.conv_t(x)
x = self.bn_t(x)
x = self.relu_t(x)
return x
class SE_Block(nn.Module):
"credits: https://github.com/moskomule/senet.pytorch/blob/master/senet/se_module.py#L4"
def __init__(self, c, r=16):
super().__init__()
self.squeeze = nn.AdaptiveAvgPool2d(1)
self.excitation = nn.Sequential(
nn.Linear(c, c // r, bias=False),
nn.ReLU(inplace=True),
nn.Linear(c // r, c, bias=False),
nn.Sigmoid()
)
def forward(self, x):
bs, c, _, _ = x.shape
y = self.squeeze(x).view(bs, c)
y = self.excitation(y).view(bs, c, 1, 1)
return x * y.expand_as(x)
我檢查了兩個引數，torch.stack但兩者的大小相同。
uj5u.com熱心網友回復：
請參閱https://pytorch.org/docs/stable/generated/torch.stack.html。
torch.stack(tensors, dim=0, *, out=None) → Tensor
tensors (sequence of Tensors) – sequence of tensors to concatenate
張量序列可以是元組(tensor1, tensor2, tensor3)或串列[tensor1, tensor2, tensor3]。您所做的是輸入x張量而不是張量序列，并weighted_channels作為函式的 dim 引數。
因此，正如評論中所指出的那樣，
torch.stack((x, weighted_channels))或者torch.stack([x, weighted_channels])應該作業。
請記住，這對于所有采用任意數量張量并對其進行處理的函式都是相同的，例如torch.cat，以及所有其他堆疊函式vstack，例如hstack-
轉載請註明出處，本文鏈接：https://www.uj5u.com/qukuanlian/468343.html
上一篇：Numpy中的像素操作