Hello all, This might be a quite trivial issue but I am not able to find the error. I am experimenting with TCNs and instead of using fully connected at the output, I am trying to make it a fully Convolutional network. I am not able to understand what shape should be passed to the loss function. The model class is the following -
class Chomp1d(nn.Module):
def __init__(self, chomp_size):
super(Chomp1d, self).__init__()
self.chomp_size = chomp_size
def forward(self, x):
return x[:, :, :-self.chomp_size].contiguous()
class TemporalBlock(nn.Module):
def __init__(self, n_inputs, n_outputs, kernel_size, stride, dilation, padding, dropout=0.2):
super(TemporalBlock, self).__init__()
self.conv1 = weight_norm(nn.Conv1d(n_inputs, n_outputs, kernel_size,
stride=stride, padding=padding, dilation=dilation))
self.chomp1 = Chomp1d(padding)
self.relu1 = nn.ReLU()
self.dropout1 = nn.Dropout(dropout)
self.conv2 = weight_norm(nn.Conv1d(n_outputs, n_outputs, kernel_size,
stride=stride, padding=padding, dilation=dilation))
self.chomp2 = Chomp1d(padding)
self.relu2 = nn.ReLU()
self.dropout2 = nn.Dropout(dropout)
self.net = nn.Sequential(self.conv1, self.chomp1, self.relu1, self.dropout1,
self.conv2, self.chomp2, self.relu2, self.dropout2)
self.downsample = nn.Conv1d(n_inputs, n_outputs, 1) if n_inputs != n_outputs else None
self.relu = nn.ReLU()
self.init_weights()
def init_weights(self):
self.conv1.weight.data.normal_(0, 0.01)
self.conv2.weight.data.normal_(0, 0.01)
if self.downsample is not None:
self.downsample.weight.data.normal_(0, 0.01)
def forward(self, x):
out = self.net(x)
res = x if self.downsample is None else self.downsample(x)
return self.relu(out + res)
class TemporalConvNet(nn.Module):
def __init__(self, num_inputs, num_channels, kernel_size=2, dropout=0.2):
super(TemporalConvNet, self).__init__()
layers = []
num_levels = len(num_channels)
for i in range(num_levels):
dilation_size = 2 ** i
in_channels = num_inputs if i == 0 else num_channels[i-1]
out_channels = num_channels[i]
layers += [TemporalBlock(in_channels, out_channels, kernel_size, stride=1, dilation=dilation_size,
padding=(kernel_size-1) * dilation_size, dropout=dropout)]
self.feature_map = nn.Conv1d(22, 512, 1)
self.network = nn.Sequential(*layers)
self.classify = nn.Conv1d(in_channels=512, out_channels=4, kernel_size=1)
def forward(self, x):
out = self.network(x)
out1 = self.feature_map(x)
out = nn.functional.relu(out+out1)
out = self.classify(out)
return out
Input shape is [22, 512] #channels, length It is a time series data and the 5 is the batch size and I have 4 output classes.
The error I get while calculating loss is
Expected target size (5, 313), got torch.Size([5])
TIA