Error is resolved
N1
class ResNet(nn.Module):
def __init__(self, block, num_blocks):
super(ResNet, self).__init__()
self.in_planes = 64
self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)
self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)
self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)
self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)
self.linear = nn.Linear(512*block.expansion, 1)
def _make_layer(self, block, planes, num_blocks, stride):
strides = [stride] + [1]*(num_blocks-1)
layers = []
for stride in strides:
layers.append(block(self.in_planes, planes, stride))
self.in_planes = planes * block.expansion
return nn.Sequential(*layers)
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = self.layer1(out)
out = self.layer2(out)
out = self.layer3(out)
out = self.layer4(out)
out = F.avg_pool2d(out, 4)
out = out.view(out.size(0), -1)
out = self.linear(out)
#print("Output of N1:" , out.shape)
return out```
N2 is
class ResNetFullyConnected(nn.Module):
def init(self, block, num_blocks, num_classes=10):
super(ResNetFullyConnected, self).init()
self.in_planes = 64
num_neurons = 64 # replace with the number of neurons you need
self.flatten = nn.Flatten() # Add a Flatten layer
self.fc1 = nn.Linear(32*32*3, num_neurons)
self.bn1 = nn.BatchNorm1d(num_neurons)
self.layer1 = self._make_layer(block, num_neurons, num_neurons, num_blocks[0])
self.layer2 = self._make_layer(block, num_neurons, num_neurons, num_blocks[1])
self.layer3 = self._make_layer(block, num_neurons, num_neurons, num_blocks[2])
self.layer4 = self._make_layer(block, num_neurons, num_neurons, num_blocks[3])
self.fc2 = nn.Linear(num_neurons, num_classes)
def _make_layer(self, block, in_features, out_features, num_blocks):
layers = []
for _ in range(num_blocks):
layers.append(block(in_features, out_features))
return nn.Sequential(*layers)
def forward(self, x):
out = F.relu(self.bn1(self.fc1(self.flatten(x))))
out = self.layer2(out)
out = self.layer3(out)
out = self.layer4(out)
out = self.fc2(out)
return out
Code of Adapter
class Adapter(nn.Module):
def init(self, in_features, out_features):
super(Adapter, self).init()
self.linear = nn.Linear(in_features, out_features)
def forward(self, x):
#x = x.flatten(start_dim=1) # Reshape the input tensor
#x = x.view(x.size(0), -1) # Flatten the input tensor
#x = self.flatten(x)
#x = x.reshape(x.size(0), -1)
x = self.linear(x)
return x
adapter = Adapter(512, 3072).cuda()
The error is mat1 and mat2 shapes cannot be multiplied (128x1 and 512x3072)