I am trying to learn about pack_padded_sequence more and want to test it in this small dataset. I managed to merge two tensors of different sequence length but when I try to pad the sequence it gives me an error. Does anybody know how to solve this? I am trying to follow an example given in the stackoverflow comments but with an actual dataset. https://stackoverflow.com/questions/51030782/why-do-we-pack-the-sequences-in-pytorch

Runtime Error: The expanded size of the tensor (8) must match the existing size (4) at non-singleton dimension 1. Target sizes: [93, 8, 1]. Tensor sizes: [93, 4, 1]

```
!wget https://raw.githubusercontent.com/jbrownlee/Datasets/master/airline-passengers.csv
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import torch
import torch.nn as nn
from torch.autograd import Variable
from sklearn.preprocessing import MinMaxScaler
training_set = pd.read_csv('airline-passengers.csv')
def sliding_windows(data, seq_length):
x = []
y = []
for i in range(len(data)-seq_length-1):
_x = data[i:(i+seq_length)]
_y = data[i+seq_length]
x.append(_x)
y.append(_y)
return x,np.array(y)
sc = MinMaxScaler()
training_data = sc.fit_transform(training_set)
seq_length = 8
x, y = sliding_windows(training_data, seq_length)
train_size = int(len(y) * 0.67)
test_size = len(y) - train_size
trainX = Variable(torch.Tensor(np.array(x[0:train_size])))
trainY = Variable(torch.Tensor(np.array(y[0:train_size])))
seq_length = 4
x1, y1 = sliding_windows(training_data, seq_length)
train_size = int(len(y1) * 0.67)
test_size = len(y1) - train_size
trainX1 = Variable(torch.Tensor(np.array(x1[0:train_size])))
trainY1 = Variable(torch.Tensor(np.array(y1[0:train_size])))
seq_batch = [trainX,
trainX1]
seq_lens = [8, 4]
added_seq_batch = torch.nn.utils.rnn.pad_sequence(seq_batch, batch_first=True)
```