I am working with sequences of images for a binary classification. With batch size 1 my sequence has dimension [1, 9, 3, 256, 256]. Since I want to use a Temporal CN (from this GitHub: TCN/TCN/mnist_pixel at master · locuslab/TCN · GitHub), which requires input size [N, C_in, L_in], I am reshaping the the images like this: images = images.view(-1, 3, 9) where 3 is the channel size and 9 the sequence length. However, I get the following error when calling loss = criterion(outputs, labels):
The size of tensor a (9) must match the size of tensor b (65536) at non-singleton dimension 0
The 65536 results from 256*256 but I don’t know how to adjust my dimensions accordingly so that they match my labels’ dimensions.
The model looks like this
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.network = nn.Sequential(*layers)
def forward(self, x):
return self.network(x)
class TCN(nn.Module):
def __init__(self, input_size, output_size, num_channels, kernel_size, dropout):
super(TCN, self).__init__()
self.tcn = TemporalConvNet(input_size, num_channels, kernel_size=kernel_size, dropout=dropout)
self.linear = nn.Linear(num_channels[-1], output_size)
def forward(self, inputs):
y1 = self.tcn(inputs) # input should have dimension (N, C, L)
o = self.linear(y1[:, :, -1])
return F.log_softmax(o, dim=1)