fix the imprecise description (d2l-ai#1168)

Co-authored-by: yuande <yuande>

Author: LaoLiulaoliu

chapter_recurrent-neural-networks/sequence.md

@@ -424,23 +424,23 @@ max_steps = 64
 ```{.python .input}
 #@tab mxnet, pytorch
 features = d2l.zeros((T - tau - max_steps + 1, tau + max_steps))
-# 列i（i<tau）是来自x的观测，其时间步从（i+1）到（i+T-tau-max_steps+1）
+# 列i（i<tau）是来自x的观测，其时间步从（i）到（i+T-tau-max_steps+1）
 for i in range(tau):
     features[:, i] = x[i: i + T - tau - max_steps + 1]
 
-# 列i（i>=tau）是来自（i-tau+1）步的预测，其时间步从（i+1）到（i+T-tau-max_steps+1）
+# 列i（i>=tau）是来自（i-tau+1）步的预测，其时间步从（i）到（i+T-tau-max_steps+1）
 for i in range(tau, tau + max_steps):
     features[:, i] = d2l.reshape(net(features[:, i - tau: i]), -1)
 ```
 
 ```{.python .input}
 #@tab tensorflow
 features = tf.Variable(d2l.zeros((T - tau - max_steps + 1, tau + max_steps)))
-# 列i（i<tau）是来自x的观测，其时间步从（i+1）到（i+T-tau-max_steps+1）
+# 列i（i<tau）是来自x的观测，其时间步从（i）到（i+T-tau-max_steps+1）
 for i in range(tau):
     features[:, i].assign(x[i: i + T - tau - max_steps + 1].numpy())
 
-# 列i（i>=tau）是来自（i-tau+1）步的预测，其时间步从（i+1）到（i+T-tau-max_steps+1）
+# 列i（i>=tau）是来自（i-tau+1）步的预测，其时间步从（i）到（i+T-tau-max_steps+1）
 for i in range(tau, tau + max_steps):
     features[:, i].assign(d2l.reshape(net((features[:, i - tau: i])), -1))
 ```

chapter_recurrent-neural-networks/sequence_origin.md

@@ -355,12 +355,12 @@ max_steps = 64
 #@tab mxnet, pytorch
 features = d2l.zeros((T - tau - max_steps + 1, tau + max_steps))
 # Column `i` (`i` < `tau`) are observations from `x` for time steps from
-# `i + 1` to `i + T - tau - max_steps + 1`
+# `i` to `i + T - tau - max_steps + 1`
 for i in range(tau):
     features[:, i] = x[i: i + T - tau - max_steps + 1].T
 
 # Column `i` (`i` >= `tau`) are the (`i - tau + 1`)-step-ahead predictions for
-# time steps from `i + 1` to `i + T - tau - max_steps + 1`
+# time steps from `i` to `i + T - tau - max_steps + 1`
 for i in range(tau, tau + max_steps):
     features[:, i] = d2l.reshape(net(features[:, i - tau: i]), -1)
 ```
@@ -369,12 +369,12 @@ for i in range(tau, tau + max_steps):
 #@tab tensorflow
 features = tf.Variable(d2l.zeros((T - tau - max_steps + 1, tau + max_steps)))
 # Column `i` (`i` < `tau`) are observations from `x` for time steps from
-# `i + 1` to `i + T - tau - max_steps + 1`
+# `i` to `i + T - tau - max_steps + 1`
 for i in range(tau):
     features[:, i].assign(x[i: i + T - tau - max_steps + 1].numpy().T)
 
 # Column `i` (`i` >= `tau`) are the (`i - tau + 1`)-step-ahead predictions for
-# time steps from `i + 1` to `i + T - tau - max_steps + 1`
+# time steps from `i` to `i + T - tau - max_steps + 1`
 for i in range(tau, tau + max_steps):
     features[:, i].assign(d2l.reshape(net((features[:, i - tau: i])), -1))
 ```