modify comments

.gitignore

@@ -2,3 +2,4 @@
 data/
 venv/
 .data/
+saved/

models/layers/multi_head_attention.py

@@ -26,7 +26,6 @@ def forward(self, q, k, v, mask=None):
  q, k, v = self.project(q), self.project(k), self.project(v)
 
  # 3, do scale dot product to compute similarity
-
  out, attention = self.attention(q, k, v, mask=mask)
  out = self.concat(out)
 

models/model/decoder.py

@@ -25,14 +25,14 @@ def __init__(self, dec_voc_size, max_len, d_model, ffn_hidden, n_head, n_layers,
  drop_prob=drop_prob)
  for _ in range(n_layers)])
 
- self.fc_out = nn.Linear(d_model, dec_voc_size)
+ self.linear = nn.Linear(d_model, dec_voc_size)
 
  def forward(self, trg, enc_src, trg_mask, src_mask):
  trg = self.emb(trg)
 
  for layer in self.layers:
  trg = layer(trg, enc_src, trg_mask, src_mask)
 
- output = self.fc_out(trg)
+ output = self.linear(trg)
 
  return output

saved/__init__.py

@@ -0,0 +1,5 @@
+"""
+@author : Hyunwoong
+@when : 2019-12-18
+@homepage : https://github.com/gusdnd852
+"""

train.py

@@ -97,7 +97,7 @@ def run(total_epoch, best_loss):
 
  if valid_loss < best_loss:
  best_loss = valid_loss
- torch.save(model.state_dict(), 'model-{0}.pt'.format(valid_loss))
+ torch.save(model.state_dict(), 'saved/model-{0}.pt'.format(valid_loss))
 
  print(f'Epoch: {step + 1} | Time: {epoch_mins}m {epoch_secs}s')
  print(f'\tTrain Loss: {train_loss:.3f} | Train PPL: {math.exp(train_loss):7.3f}')