torch type mismatch error about speech HOT 9 OPEN

diff --git a/speech/models/seq2seq.py b/speech/models/seq2seq.py
index b2881e3..65e3a38 100644
--- a/speech/models/seq2seq.py
+++ b/speech/models/seq2seq.py
@@ -87,7 +87,7 @@ class Seq2Seq(model.Model):

         hx = torch.zeros((x.shape[0], x.shape[2]), requires_grad=False)
         if self.is_cuda:
-            hx.cuda()
+            hx = hx.cuda()
         ax = None; sx = None;
         for t in range(y.size()[1] - 1):
             sample = (out and self.scheduled_sampling)
@@ -119,7 +119,7 @@ class Seq2Seq(model.Model):
         if state is None:
             hx = torch.zeros((x.shape[0], x.shape[2]), requires_grad=False)
             if self.is_cuda:
-                hx.cuda()
+                hx = hx.cuda()
             ax = None; sx = None;
         else:
             hx, ax, sx = state
@@ -164,7 +164,7 @@ class Seq2Seq(model.Model):
         Infer a likely output. No beam search yet.
         """
         x, y = self.collate(*batch)
-        end_tok = y.data[0, -1] # TODO
+        end_tok = y.data[0, -1].cuda() # TODO
         t = y
         if self.is_cuda:
             x = x.cuda()
@@ -172,7 +172,7 @@ class Seq2Seq(model.Model):
         x = self.encode(x)

         # needs to be the start token, TODO
-        y = t[:, 0:1]
+        y = t[:, 0:1].cuda()
         _, argmaxs = self.infer_decode(x, y, end_tok, max_len)
         argmaxs = argmaxs.cpu().data.numpy()
         return [seq.tolist() for seq in argmaxs]

diff --git a/train.py b/train.py
index a04eb6c..6141ba0 100644
--- a/train.py
+++ b/train.py
@@ -10,6 +10,7 @@ import torch
 import torch.nn as nn
 import torch.optim
 import tqdm
+import copy

 import speech
 import speech.loader as loader
@@ -30,7 +31,7 @@ def run_epoch(model, optimizer, train_ldr, it, avg_loss):
         loss.backward()

         grad_norm = nn.utils.clip_grad_norm(model.parameters(), 200)
-        loss = loss.data[0]
+        loss = loss.item()

         optimizer.step()
         prev_end_t = end_t
@@ -54,11 +55,13 @@ def eval_dev(model, ldr, preproc):
     model.set_eval()

     for batch in tqdm.tqdm(ldr):
-        preds = model.infer(batch)
-        loss = model.loss(batch)
-        losses.append(loss.data[0])
+        batch_ = copy.deepcopy(batch)
+        preds = model.infer(batch_)
+        batch_ = copy.deepcopy(batch)
+        loss = model.loss(batch_)
+        losses.append(loss.item())
         all_preds.extend(preds)
-        all_labels.extend(batch[1])
+        all_labels.extend(list(batch)[1])

     model.set_train()

$ python train.py examples/timit/seq2seq_config.json
Traceback (most recent call last):
  File "train.py", line 146, in <module>
    run(config)
  File "train.py", line 104, in run
    run_state = run_epoch(model, optimizer, train_ldr, *run_state)
  File "train.py", line 29, in run_epoch
    loss = model.loss(batch)
  File "/path/to/speech/models/seq2seq.py", line 57, in loss
    out, alis = self.forward_impl(x, y)
  File "/path/to/speech/models/seq2seq.py", line 68, in forward_impl
    out, alis = self.decode(x, y)
  File "/path/to/speech/models/seq2seq.py", line 103, in decode
    hx = self.dec_rnn(ix.squeeze(dim=1), hx)
  File "/path/to/lib64/python3.6/site-packages/torch/nn/modules/module.py", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "/path/to/lib64/python3.6/site-packages/torch/nn/modules/rnn.py", line 794, in forward
    self.bias_ih, self.bias_hh,
  File "/path/to/lib64/python3.6/site-packages/torch/nn/_functions/rnn.py", line 53, in GRUCell
    gh = F.linear(hidden, w_hh)
  File "/path/to/lib64/python3.6/site-packages/torch/nn/functional.py", line 1026, in linear
    output = input.matmul(weight.t())
RuntimeError: Expected object of type torch.FloatTensor but found type torch.cuda.FloatTensor for argument #2 'mat2'

def check_type(var, t, name):
    #if type(var) is not t:
    if var.type() != str(t).split("'")[1]:
        raise TypeError("{} must be {},\n{},\n{}".format(name, t,A,B))

def certify_inputs(log_probs, labels, lengths, label_lengths):
    if log_probs.is_cuda:
        check_type(log_probs, torch.cuda.FloatTensor, "log_probs")
    else:
        check_type(log_probs, torch.FloatTensor, "log_probs")

    if labels.is_cuda:
        check_type(labels, torch.cuda.IntTensor, "labels")
    else:
        check_type(labels, torch.IntTensor, "labels")
    if label_lengths.is_cuda:
        check_type(label_lengths, torch.cuda.IntTensor, "label_lengths")
    else:
        check_type(label_lengths, torch.IntTensor, "label_lengths")

    if lengths.is_cuda:
        check_type(lengths, torch.cuda.IntTensor, "lengths")
    else:
        check_type(lengths, torch.IntTensor, "lengths")
   ..........

    def forward(self, log_probs, labels, lengths, label_lengths):
        """
        Computes the Transducer cost for a minibatch of examples.

        Arguments:
            log_probs (FloatTensor): The log probabilities should
                be of shape
                (minibatch, input len, output len, vocab size).
            labels (IntTensor): 1D tensor of labels for each example
                consecutively.
            lengths (IntTensor): 1D tensor of number actviation time-steps
                for each example.
            label_lengths (IntTensor): 1D tensor of label lengths for
                each example.

        Returns:
            costs (FloatTensor): .
        """
        is_cuda = log_probs.is_cuda
        certify_inputs(log_probs, labels, lengths, label_lengths)
        log_probs = log_probs.cpu()
        labels = labels.cpu() 
        lengths = lengths.cpu()
        label_lengths = label_lengths.cpu()
        ...............

WARNING: Forward backward likelihood mismatch 0.000084
WARNING: Forward backward likelihood mismatch 0.000092
WARNING: Forward backward likelihood mismatch 0.000046