Python tensorflow中的值错误和馈送

ValueError：无法为具有形状“（28，7，22）”的张量“占位符：0”输入形状（942，22）的值

有人能告诉我如何将数据输入basicRNN单元格吗？下面是tensorflow代码的一部分

num_inputs = 22

timesteps = 7

batch_size = 28

x=tf.placeholder(tf.float32,shape=(batch_size,timesteps,num_inputs))
y=tf.placeholder(tf.float32,shape=(batch_size,timesteps,num_outputs))

---

with tf.Session(config= tf.ConfigProto(gpu_options=gpu_options)) as sess:
    sess.run(init)

for iteration in range(num_iterations):
    sess.run(train,feed_dict={x:X_train,y:y_train} )        
    if iteration % 100==0:
       mse=loss.eval(feed_dict={x:X_train,y:y_train})
       print(mse)

saver.save(sess,"./rnn_model")