I also have the same kind of error, RuntimeError: Given groups=1, weight of size [16, 256, 1, 1], expected input[1, 1024, 1, 1] to have 256 channels, but got 1024 channels instead. My code is given below
āā'class Attention(nn.Module):
def init(self, in_planes, out_planes, kernel_size, groups=1, reduction=0.0625, kernel_num=4, min_channel=16):
super(Attention, self).init()
attention_channel = max(int(in_planes * reduction), min_channel)
self.kernel_size = kernel_size
self.kernel_num = kernel_num
self.temperature = 1.0
self.avgpool = nn.AdaptiveAvgPool2d(1)
self.fc = nn.Conv2d(in_planes, attention_channel, 1, bias=False)
self.bn = nn.BatchNorm2d(attention_channel)
self.relu = nn.ReLU(inplace=True)
self.channel_fc = nn.Conv2d(attention_channel, in_planes, 1, bias=True)
self.func_channel = self.get_channel_attention
if in_planes == groups and in_planes == out_planes: # depth-wise convolution
self.func_filter = self.skip
else:
self.filter_fc = nn.Conv2d(attention_channel, out_planes, 1, bias=True)
self.func_filter = self.get_filter_attention
if kernel_size == 1: # point-wise convolution
self.func_spatial = self.skip
else:
self.spatial_fc = nn.Conv2d(attention_channel, kernel_size * kernel_size, 1, bias=True)
self.func_spatial = self.get_spatial_attention
if kernel_num == 1:
self.func_kernel = self.skip
else:
self.kernel_fc = nn.Conv2d(attention_channel, kernel_num, 1, bias=True)
self.func_kernel = self.get_kernel_attention
self._initialize_weights()
def _initialize_weights(self):
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
if m.bias is not None:
nn.init.constant_(m.bias, 0)
if isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
def update_temperature(self, temperature):
self.temperature = temperature
@staticmethod
def skip(_):
return 1.0
def get_channel_attention(self, x):
channel_attention = torch.sigmoid(self.channel_fc(x).view(x.size(0), -1, 1, 1) / self.temperature)
return channel_attention
def get_filter_attention(self, x):
filter_attention = torch.sigmoid(self.filter_fc(x).view(x.size(0), -1, 1, 1) / self.temperature)
return filter_attention
def get_spatial_attention(self, x):
spatial_attention = self.spatial_fc(x).view(x.size(0), 1, 1, 1, self.kernel_size, self.kernel_size)
spatial_attention = torch.sigmoid(spatial_attention / self.temperature)
return spatial_attention
def get_kernel_attention(self, x):
kernel_attention = self.kernel_fc(x).view(x.size(0), -1, 1, 1, 1, 1)
kernel_attention = F.softmax(kernel_attention / self.temperature, dim=1)
return kernel_attention
def forward(self, x):
x = self.avgpool(x)
x = self.fc(x)
x = self.bn(x)
x = self.relu(x)
return self.func_channel(x), self.func_filter(x), self.func_spatial(x), self.func_kernel(x)
class ODConv2d(nn.Module):
def init(self, in_planes, out_planes, kernel_size, stride=1, padding=None, dilation=1, groups=1,
reduction=0.0625, kernel_num=4):
super(ODConv2d, self).init()
self.in_planes = in_planes
self.out_planes = out_planes
self.kernel_size = kernel_size
self.stride = stride
self.padding = padding
self.dilation = dilation
self.groups = groups
self.kernel_num = kernel_num
self.attention = Attention(in_planes, out_planes, kernel_size, groups=groups,
reduction=reduction, kernel_num=kernel_num)
self.weight = nn.Parameter(torch.randn(kernel_num, out_planes, in_planes//groups, kernel_size, kernel_size),
requires_grad=True)
self._initialize_weights()
if self.kernel_size == 1 and self.kernel_num == 1:
self._forward_impl = self._forward_impl_pw1x
else:
self._forward_impl = self._forward_impl_common
def _initialize_weights(self):
for i in range(self.kernel_num):
nn.init.kaiming_normal_(self.weight[i], mode='fan_out', nonlinearity='relu')
def update_temperature(self, temperature):
self.attention.update_temperature(temperature)
def _forward_impl_common(self, x):
# Multiplying channel attention (or filter attention) to weights and feature maps are equivalent,
# while we observe that when using the latter method the models will run faster with less gpu memory cost.
channel_attention, filter_attention, spatial_attention, kernel_attention = self.attention(x)
batch_size, in_planes, height, width = x.size()
x = x * channel_attention
x = x.reshape(1, -1, height, width)
aggregate_weight = spatial_attention * kernel_attention * self.weight.unsqueeze(dim=0)
aggregate_weight = torch.sum(aggregate_weight, dim=1).view(
[-1, self.in_planes // self.groups, self.kernel_size, self.kernel_size])
output = F.conv2d(x, weight=aggregate_weight, bias=None, stride=self.stride, padding=self.padding,
dilation=self.dilation, groups=self.groups * batch_size)
output = output.view(batch_size, self.out_planes, output.size(-2), output.size(-1))
output = output * filter_attention
print(output)
return output
def _forward_impl_pw1x(self, x):
channel_attention, filter_attention, spatial_attention, kernel_attention = self.attention(x)
x = x * channel_attention
output = F.conv2d(x, weight=self.weight.squeeze(dim=0), bias=None, stride=self.stride, padding=self.padding,
dilation=self.dilation, groups=self.groups)
output = output * filter_attention
return output
def forward(self, x):
return self._forward_impl(x)'''
āā'def autopad(k, p=None): # kernel, padding
# Pad to āsameā
if p is None:
p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad
return p
def ODautopad(kernel_size, padding=None): # kernel, padding
# Pad to āsameā
if padding is None:
padding = kernel_size // 2 if isinstance(kernel_size, int) else [x // 2 for x in kernel_size] # auto-pad
return padding
class Conv(nn.Module):
# Standard convolution
def init(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
super(Conv, self).init()
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
self.bn = nn.BatchNorm2d(c2)
self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
def forward(self, x):
return self.act(self.bn(self.conv(x)))
def fuseforward(self, x):
return self.act(self.conv(x))
class ODConvBNReLU(nn.Module):
def init(self, in_planes, out_planes, kernel_size=1, stride=1, padding=None, groups=1, norm_layer=nn.BatchNorm2d,
reduction=0.0625, kernel_num=1):
super(ODConvBNReLU, self).init()
self.conv = ODConv2d(in_planes, out_planes, kernel_size, stride, ODautopad(kernel_size, padding), groups=groups,
reduction=reduction, kernel_num=kernel_num)
self.bn = norm_layer(out_planes)
self.relu = nn.ReLU6(inplace=True)
def forward(self, x):
x = self.conv(x)
x = self.bn(x)
x = self.relu(x)
return x'''
The ymal file is
yolov7 backbone
backbone:
[from, number, module, args]
[[-1, 1, Conv, [32, 3, 1]], # 0
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
[-1, 1, Conv, [64, 3, 1]],
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
[-1, 1, Conv, [64, 1, 1]],
[-2, 1, Conv, [64, 1, 1]],
[-1, 1, Conv, [64, 3, 1]],
[-1, 1, Conv, [64, 3, 1]],
[-1, 1, Conv, [64, 3, 1]],
[-1, 1, Conv, [64, 3, 1]],
[[-1, -3, -5, -6], 1, Concat, [1]],
[-1, 1, Conv, [256, 1, 1]], # 11
[-1, 1, MP, ],
[-1, 1, Conv, [128, 1, 1]],
[-3, 1, Conv, [128, 1, 1]],
[-1, 1, Conv, [128, 3, 2]],
[[-1, -3], 1, Concat, [1]], # 16-P3/8
[-1, 1, Conv, [128, 1, 1]],
[-2, 1, Conv, [128, 1, 1]],
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, Conv, [128, 3, 1]],
[[-1, -3, -5, -6], 1, Concat, [1]],
[-1, 1, Conv, [512, 1, 1]], # 24
[-1, 1, MP, ],
[-1, 1, Conv, [256, 1, 1]],
[-3, 1, Conv, [256, 1, 1]],
[-1, 1, Conv, [256, 3, 2]],
[[-1, -3], 1, Concat, [1]], # 29-P4/16
[-1, 1, Conv, [256, 1, 1]],
[-2, 1, Conv, [256, 1, 1]],
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, Conv, [256, 3, 1]],
[[-1, -3, -5, -6], 1, Concat, [1]],
[-1, 1, Conv, [1024, 1, 1]], # 37
[-1, 1, MP, ],
[-1, 1, Conv, [512, 1, 1]],
[-3, 1, Conv, [512, 1, 1]],
[-1, 1, Conv, [512, 3, 2]],
[[-1, -3], 1, Concat, [1]], # 42-P5/32
[-1, 1, Conv, [256, 1, 1]],
[-2, 1, Conv, [256, 1, 1]],
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, Conv, [256, 3, 1]],
[[-1, -3, -5, -6], 1, Concat, [1]],
[-1, 1, Conv, [1024, 1, 1]], # 50
]
yolov7 head
head:
[[-1, 1, SPPCSPC, [512]], # 51
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, ānearestā]],
[37, 1, ODConvBNReLU, [256, 1, 1]], # route backbone P4
[[-1, -2], 1, Concat, [1]],
[-1, 1, Conv, [256, 1, 1]],
[-2, 1, Conv, [256, 1, 1]],
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, Conv, [128, 3, 1]],
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
[-1, 1, Conv, [256, 1, 1]], # 63
[-1, 1, Conv, [128, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, ānearestā]],
[24, 1, ODConvBNReLU, [128, 1, 1]], # route backbone P3
[[-1, -2], 1, Concat, [1]],
[-1, 1, Conv, [128, 1, 1]],
[-2, 1, Conv, [128, 1, 1]],
[-1, 1, Conv, [64, 3, 1]],
[-1, 1, Conv, [64, 3, 1]],
[-1, 1, Conv, [64, 3, 1]],
[-1, 1, Conv, [64, 3, 1]],
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
[-1, 1, Conv, [128, 1, 1]], # 75
[-1, 1, MP, ],
[-1, 1, Conv, [128, 1, 1]],
[-3, 1, Conv, [128, 1, 1]],
[-1, 1, Conv, [128, 3, 2]],
[[-1, -3, 63], 1, Concat, [1]],
[-1, 1, Conv, [256, 1, 1]],
[-2, 1, Conv, [256, 1, 1]],
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, Conv, [128, 3, 1]],
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
[-1, 1, Conv, [256, 1, 1]], # 88
[-1, 1, MP, ],
[-1, 1, Conv, [256, 1, 1]],
[-3, 1, Conv, [256, 1, 1]],
[-1, 1, Conv, [256, 3, 2]],
[[-1, -3, 51], 1, Concat, [1]],
[-1, 1, Conv, [512, 1, 1]],
[-2, 1, Conv, [512, 1, 1]],
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, Conv, [256, 3, 1]],
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
[-1, 1, Conv, [512, 1, 1]], # 101
[75, 1, RepConv, [256, 3, 1]],
[88, 1, RepConv, [512, 3, 1]],
[101, 1, RepConv, [1024, 3, 1]],
[[102,103,104], 1, IDetect, [nc, anchors]], # Detect(P3, P4, P5)
]
when i am changing to Conv to ODConvBNReLU, the above error is coming. I have tried everything but couldnot understand. In my understanding ODConvBNReLU must pass the 256 channel but it is passing 1024 channel.