Convolutional 1D NN with different sequence lengths


I have a hard time understanding the size of tensors and how they change shape thorughout my network.

My data consist of 1000s of .csv files which each have 1000s of data samples. Some have few samples like 10 some have 10.000 samples. Due to memory a single track(sequence/.csv file) must be loaded at a time. I would prefer to have the network train on a single timestep on a single file. But atm i will settle for just getting a basic working network up and run with my data. I have 3 folders, 1 folder with .csv files from each class. My end goal is to produce a classifier which can classify ship types from movement patterns. First running the through a CNN to extract features and then a RNN to produce the predicted classes. However i start out very simply with just 2 conv-layers.

My custom data.Dataset class is the following (shown here is from Cargo ships):

class cargoShipDataset(data.Dataset):
    def __init__(self, root_dir, transform=None):
        self.transform = transform
        self.list_of_data_files = glob.glob(root_dir) #Load list of all filenames in directory
        self.len = len(self.list_of_data_files)
    def __getitem__(self, index):
        single_track = torch.from_numpy(genfromtxt(self.list_of_data_files[index], delimiter=',')[1:,:]) #a single track is loaded.
        target = torch.ones(single_track.size(0)) # Class Cargo = 1 ? Class Passenger = 2 ?
        return (single_track, target)

    def __len__(self):
        return self.len

My network (stolen from
It inputs a timeseries with three channels (latitude, longitude and timestamp).

class CNN(nn.Module):
    def __init__(self):
        self.conv1 = nn.Sequential(         
                in_channels=3,              #Inputs time series, with Latitude, Longitude and Timestamp
                out_channels=16,            #Some random number
            nn.MaxPool1d(kernel_size=2),   #size after pooling?
        self.conv2 = nn.Sequential(         
        self.out = nn.Linear(8, 3)  #output 3 classes: Cargo, Passenger or Fishing
    def forward(self,x):
        x = self.conv1(x)
        x = self.conv2(x)
        output = self.out(x)
        return output

My train loop:

cnn = CNN()
optimizer = torch.optim.Adam(cnn.parameters(), lr=0.0001)   # optimize all cnn parameters
loss_func = nn.CrossEntropyLoss()                       # the target label is not one-hotted

for epoch in range(1):
    for step, data in enumerate(train_set_cargo):   # gives batch data, normalize x when iterate train_loader
        b_x = data[0] #here b_x is a tensor with size [sequence length, 3] Where the values are: lat, lon, time.
        b_y = data[1] #b_y is a tensor with size [sequence length, 1] of simply ones.
        output = cnn(b_x)               # cnn output
        loss = loss_func(output, b_y)   # cross entropy loss
        optimizer.zero_grad()           # clear gradients for this training step
        loss.backward()                 # backpropagation, compute gradients
        optimizer.step()                # apply gradients

The problem is that b_x is of size [sequence length , 3] when printing it pre output = cnn(b_x). However, when printing it inside the Network code, pre x = self.conv1(x), the size is suddenly [1, sequence length, 3].

Since my network is set to convolve 1D over 3 channels is returns error cause it gets “sequence length” channels. See error below.

My traceback error snippet:

Traceback (most recent call last):

  File "<ipython-input-14-af3912e69f8b>", line 1, in <module>
    runfile('C:/Users/AWESOME-O 4000/Desktop/Speciale/Data/', wdir='C:/Users/AWESOME-O 4000/Desktop/Speciale/Data')

  File "C:\Anaconda3\lib\site-packages\spyder_kernels\customize\", line 678, in runfile
    execfile(filename, namespace)

  File "C:\Anaconda3\lib\site-packages\spyder_kernels\customize\", line 106, in execfile
    exec(compile(, filename, 'exec'), namespace)

  File "C:/Users/AWESOME-O 4000/Desktop/Speciale/Data/", line 107, in <module>
    output = cnn(b_x)               # cnn output

  File "C:\Anaconda3\lib\site-packages\torch\nn\modules\", line 477, in __call__
    result = self.forward(*input, **kwargs)

  File "C:/Users/AWESOME-O 4000/Desktop/Speciale/Data/", line 87, in forward
    x = self.conv1(x)

  File "C:\Anaconda3\lib\site-packages\torch\nn\modules\", line 477, in __call__
    result = self.forward(*input, **kwargs)

  File "C:\Anaconda3\lib\site-packages\torch\nn\modules\", line 91, in forward
    input = module(input)

  File "C:\Anaconda3\lib\site-packages\torch\nn\modules\", line 477, in __call__
    result = self.forward(*input, **kwargs)

  File "C:\Anaconda3\lib\site-packages\torch\nn\modules\", line 176, in forward
    self.padding, self.dilation, self.groups)

RuntimeError: Given groups=1, weight of size [16, 3, 5], expected input[1, 1429, 3] to have 3 channels, but got 1429 channels instead

I am very new to pytorch (still havn’t done a single network yet). And have a hard time understanding when tensors change size. Once this is fixed my next problem is that my sequences have different length, but this i will fix later :smiley:

Any help/insight is greatly appreciated. I feel like its most likely an error stemming from my custom data.Dataset or the network/training loop. Which is why i have that code pasted in.
My plan is to do 3 data.Dataset classes, one for each class. And then concanate them into one data set.

If any information is missing let me know and i will provide as best as i can.


nn.Conv1d expects your input to be [batch_size, channels, length], see the docs. Could you try to swap the axes using:

b_x = b_x.permute(0, 2, 1)

Alternatively you could reshape it in your Dataset's __getitem__ so that your training loop stays a bit cleaner.

Thank you so much for your reply.

I fixed the error by transposing the numpy array in the Dataset’s getitem as you requested :slight_smile:

The line is now:

single_track = torch.from_numpy(np.transpose(genfromtxt(self.list_of_data_files[index], delimiter=','))[:,1:])

Unfortunately a new error popped up now calling an error in the type of tensor. I use FloatTensor but it expects a DoubleTensor.

RuntimeError: Expected object of type torch.DoubleTensor but found type torch.FloatTensor for argument #2 'weight'

For what i understand its an error that occurs when it uses both cpu and gpu? I don’t know how to set which processor to use so will have to look into that :slight_smile:

Probably, you may need to call .float() on your data and models to solve this.

1 Like

Thank you! Now it works (except for my different sequence lengths, but i will look into padding now :smile: )

Hello I am new to pytorch as well - where would I insert the .float()?

So what does the final code that works look like?