RuntimeError: Expected hidden[0] size (2, 20, 256), got (2, 50, 256)

Input is a tensor from the data loader which has a batch size of 50 and sequence length of 20. Labels is uni dimensional tensor of possbile values ranging from 0 to 43 (44 values. Pls find below detailed code.

import torch.nn as nn

class ClassificationRNN(nn.Module):
“”"
The RNN model that will be used to perform Sentiment analysis.
“”"

def __init__(self, vocab_size, output_size, embedding_dim, hidden_dim, n_layers, drop_prob=0.5):
    """
    Initialize the model by setting up the layers.
    """
    super(ClassificationRNN, self).__init__()

    self.output_size = output_size
    self.n_layers = n_layers
    self.hidden_dim = hidden_dim
    
    # define all layers
    # embedding and LSTM layers
    self.embedding = nn.Embedding(vocab_size,embedding_dim)
    self.lstm = nn.LSTM(embedding_dim,hidden_dim,n_layers,dropout=drop_prob, batch_first=True)
    
    #full connected layer & softmax
    self.fc = nn.Linear(hidden_dim,output_size)
    self.sof = nn.LogSoftmax(dim=1)
    
    #dropout layer
    self.dropout = nn.Dropout(0.3)

def forward(self, x, hidden):
    """
    Perform a forward pass of our model on some input and hidden state.
    """
    batch_size = x.size(0)
    embeds = self.embedding(x)
    lstm_out,hidden= self.lstm(embeds,hidden)
    
     # stack up lstm outputs
    lstm_out = lstm_out.contiguous().view(-1, self.hidden_dim)
    
    # dropout and fully-connected layer
    out = self.dropout(lstm_out)
    out = self.fc(out)
    
    # softmax function
    soft_out = self.sof(out)
    
    # reshape to be batch_size first
    soft_out = soft_out.view(batch_size, -1)

soft_out = soft_out[:, -1] # get last batch of labels

    # return last sigmoid output and hidden state
    return soft_out, hidden


def init_hidden(self, batch_size):
    ''' Initializes hidden state '''
    # Create two new tensors with sizes n_layers x batch_size x hidden_dim,
    # initialized to zero, for hidden state and cell state of LSTM
    weight = next(self.parameters()).data
    
    if (train_on_gpu):
        hidden = (weight.new(self.n_layers, batch_size, self.hidden_dim).zero_().cuda(),
              weight.new(self.n_layers, batch_size, self.hidden_dim).zero_().cuda())
    else:
        hidden = (weight.new(self.n_layers, batch_size, self.hidden_dim).zero_(),
                  weight.new(self.n_layers, batch_size, self.hidden_dim).zero_())
    
    return hidden

Instantiate the model w/ hyperparams

vocab_size = len(vocab_to_int)+1
output_size = 44
embedding_dim = 100
hidden_dim = 256
n_layers = 2

net = ClassificationRNN(vocab_size, output_size, embedding_dim, hidden_dim, n_layers)

print(net)

loss and optimization functions

lr=0.001

criterion = nn.NLLLoss()

optimizer = torch.optim.Adam(net.parameters(), lr=lr)


training params

epochs = 4 # 3-4 is approx where I noticed the validation loss stop decreasing

counter = 0
print_every = 100
clip=5 # gradient clipping

move model to GPU, if available

if(train_on_gpu):
net.cuda()

net.train()

train for some number of epochs

for e in range(epochs):
# initialize hidden state
h = net.init_hidden(batch_size)

# batch loop
for inputs, labels in train_loader:
    counter += 1

    if(train_on_gpu):
        inputs, labels = inputs.cuda(), labels.cuda()

    # Creating new variables for the hidden state, otherwise
    # we'd backprop through the entire training history
    h = tuple([each.data for each in h])

    # zero accumulated gradients
    net.zero_grad()

    # get the output from the model
    output, h = net(inputs, h)
    
    print('output shape',output.shape)

print(‘labels:’,labels.float())

    # calculate the loss and perform backprop
    loss = criterion(output.squeeze(), labels)
    loss.backward()
    # `clip_grad_norm` helps prevent the exploding gradient problem in RNNs / LSTMs.
    nn.utils.clip_grad_norm_(net.parameters(), clip)
    optimizer.step()

    # loss stats
    if counter % print_every == 0:
        # Get validation loss
        val_h = net.init_hidden(batch_size)
        val_losses = []
        net.eval()
        for inputs, labels in valid_loader:

            # Creating new variables for the hidden state, otherwise
            # we'd backprop through the entire training history
            val_h = tuple([each.data for each in val_h])

            if(train_on_gpu):
                inputs, labels = inputs.cuda(), labels.cuda()

            output, val_h = net(inputs, val_h)
            
            val_loss = criterion(output.squeeze(), labels)

            val_losses.append(val_loss.item())

        net.train()
        print("Epoch: {}/{}...".format(e+1, epochs),
              "Step: {}...".format(counter),
              "Loss: {:.6f}...".format(loss.item()),
              "Val Loss: {:.6f}".format(np.mean(val_losses)))