Sess.run()解释下

例如：
cost=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred,labels=labels_placeholder))#交叉熵比较计算值与label
optimizer=tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)

sess.run(optimizer, feed_dict={datas_placeholder: batch_x, labels_placeholder: batch_y, dropout_placeholdr: dropout})

feed_dict将数据传入optimizer中，batch_x，batch_y，dropout分别是值