diff --git a/4-3.Bi-LSTM(Attention)/Bi-LSTM(Attention).py b/4-3.Bi-LSTM(Attention)/Bi-LSTM(Attention).py
index 7ff6365..09833dd 100644
--- a/4-3.Bi-LSTM(Attention)/Bi-LSTM(Attention).py
+++ b/4-3.Bi-LSTM(Attention)/Bi-LSTM(Attention).py
@@ -34,7 +34,7 @@ def forward(self, X):
 
         # final_hidden_state, final_cell_state : [num_layers(=1) * num_directions(=2), batch_size, n_hidden]
         output, (final_hidden_state, final_cell_state) = self.lstm(input, (hidden_state, cell_state))
-        output = output.permute(1, 0, 2) # output : [batch_size, len_seq, n_hidden]
+        output = output.permute(1, 0, 2) # output : [batch_size, len_seq, n_hidden * num_directions(=2)]
         attn_output, attention = self.attention_net(output, final_hidden_state)
         return self.out(attn_output), attention # model : [batch_size, num_classes], attention : [batch_size, n_step]