add detail about states index in rnn result, test=document_fix (#31048)

python/paddle/nn/layer/rnn.py

@@ -1132,14 +1132,16 @@ class SimpleRNN(RNNBase):
         name (str, optional): Name for the operation (optional, default is 
             None). For more information, please refer to :ref:`api_guide_Name`.
 
-    Inputs:s
+    Inputs:
         - **inputs** (Tensor): the input sequence. If `time_major` is True, the shape is `[time_steps, batch_size, input_size]`, else, the shape is `[batch_size, time_steps, hidden_size]`.
         - **initial_states** (Tensor, optional): the initial state. The shape is `[num_layers * num_directions, batch_size, hidden_size]`. If initial_state is not given, zero initial states are used.
         - **sequence_length** (Tensor, optional): shape `[batch_size]`, dtype: int64 or int32. The valid lengths of input sequences. Defaults to None. If `sequence_length` is not None, the inputs are treated as padded sequences. In each input sequence, elements whose time step index are not less than the valid length are treated as paddings.
 
     Returns:
+
         - **outputs** (Tensor): the output sequence. If `time_major` is True, the shape is `[time_steps, batch_size, num_directions * hidden_size]`, else, the shape is `[batch_size, time_steps, num_directions * hidden_size]`. Note that `num_directions` is 2 if direction is "bidirectional" else 1.
-        - **final_states** (Tensor): final states. The shape is `[num_layers * num_directions, batch_size, hidden_size]`. Note that `num_directions` is 2 if direction is "bidirectional" else 1.
+        
+        - **final_states** (Tensor): final states. The shape is `[num_layers * num_directions, batch_size, hidden_size]`. Note that `num_directions` is 2 if direction is "bidirectional" (the index of forward states are 0, 2, 4, 6... and the index of backward states are 1, 3, 5, 7...), else 1.
 
     Variables:
         - **weight_ih_l[k]**: the learnable input-hidden weights of the k-th layer. If `k = 0`, the shape is `[hidden_size, input_size]`. Otherwise, the shape is `[hidden_size, num_directions * hidden_size]`.
@@ -1252,8 +1254,10 @@ class LSTM(RNNBase):
         - **sequence_length** (Tensor, optional): shape `[batch_size]`, dtype: int64 or int32. The valid lengths of input sequences. Defaults to None. If `sequence_length` is not None, the inputs are treated as padded sequences. In each input sequence, elements whos time step index are not less than the valid length are treated as paddings.
 
     Returns:
-        - **outputs** (Tensor): the output sequence. If `time_major` is True, the shape is `[time_steps, batch_size, num_directions * hidden_size]`, If `time_major` is False, the shape is `[batch_size, time_steps, num_directions * hidden_size]`. Note that `num_directions` is 2 if direction is "bidirectional" else 1. 
-        - **final_states** (tuple): the final state, a tuple of two tensors, h and c. The shape of each is `[num_layers * num_directions, batch_size, hidden_size]`. Note that `num_directions` is 2 if direction is "bidirectional" else 1.
+
+        - **outputs** (Tensor): the output sequence. If `time_major` is True, the shape is `[time_steps, batch_size, num_directions * hidden_size]`, If `time_major` is False, the shape is `[batch_size, time_steps, num_directions * hidden_size]`. Note that `num_directions` is 2 if direction is "bidirectional" else 1.
+        
+        - **final_states** (tuple): the final state, a tuple of two tensors, h and c. The shape of each is `[num_layers * num_directions, batch_size, hidden_size]`. Note that `num_directions` is 2 if direction is "bidirectional" (the index of forward states are 0, 2, 4, 6... and the index of backward states are 1, 3, 5, 7...), else 1.
 
     Variables:
         - **weight_ih_l[k]**: the learnable input-hidden weights of the k-th layer. If `k = 0`, the shape is `[hidden_size, input_size]`. Otherwise, the shape is `[hidden_size, num_directions * hidden_size]`.
@@ -1357,8 +1361,10 @@ class GRU(RNNBase):
         - **sequence_length** (Tensor, optional): shape `[batch_size]`, dtype: int64 or int32. The valid lengths of input sequences. Defaults to None. If `sequence_length` is not None, the inputs are treated as padded sequences. In each input sequence, elements whos time step index are not less than the valid length are treated as paddings.
 
     Returns:
+
         - **outputs** (Tensor): the output sequence. If `time_major` is True, the shape is `[time_steps, batch_size, num_directions * hidden_size]`, else, the shape is `[batch_size, time_steps, num_directions * hidden_size]`. Note that `num_directions` is 2 if direction is "bidirectional" else 1.
-        - **final_states** (Tensor): final states. The shape is `[num_layers * num_directions, batch_size, hidden_size]`. Note that `num_directions` is 2 if direction is "bidirectional" else 1.
+        
+        - **final_states** (Tensor): final states. The shape is `[num_layers * num_directions, batch_size, hidden_size]`. Note that `num_directions` is 2 if direction is "bidirectional" (the index of forward states are 0, 2, 4, 6... and the index of backward states are 1, 3, 5, 7...), else 1.
 
     Variables:
         - **weight_ih_l[k]**: the learnable input-hidden weights of the k-th layer. If `k = 0`, the shape is `[hidden_size, input_size]`. Otherwise, the shape is `[hidden_size, num_directions * hidden_size]`.