I want the output to be 12 x 2 so i can classify the text
I used Dataloader to feed lstm with 32 batch_size but when I want to predict it return 3 dimension
class lstm(nn.Module):
def __init__(self,vocab_size,hidden_dim,n_classes,bs):
super(lstm,self).__init__()
self.bs = bs
self.hidden_dim = hidden_dim
self.hidden = self.init_hidden(bs)
self.e = nn.Embedding(vocab_size,n_fac)
self.lstm = nn.LSTM(n_fac,hidden_dim)
self.out = nn.Linear(hidden_dim,n_classes)
def forward(self,cs):
#output e = 11,n_fac
e = self.e(cs)
#lstm need seq,bs,input_size
out_lstm,h = self.lstm(e)
#output is seq,bs,hid*num_layer
#out need sq,hidden
out = self.out(out_lstm)
return F.log_softmax(out,dim=-1)
def init_hidden(self,bs):
return (autograd.Variable(torch.zeros(1,bs,self.hidden_dim)),autograd.Variable(torch.zeros(1,bs,self.hidden_dim)))
def predict_text(text,vocab_size):
chars = vocab_size
char_indices = dict((c,i) for i,c in enumerate(chars))
idx=[char_indices[c] for c in text]
text_var = autograd.Variable(torch.LongTensor(idx))
outputs = model(text_var)
print(outputs)
return outputs
output that i got
