tensorflow中出現{TypeError}unhashable type: 'numpy.ndarray'

本人實驗中使用feed的方式填充數據，sess處的代碼如下：

with tf.Session() as sess:
    init = tf.global_variables_initializer()
    sess.run(init)
    for epoch in range(a.epochs):
        input, target = load_batch_data(batch_size=16, a=a)
        batch_input = input.astype(np.float32)
        batch_target = target.astype(np.float32)
        sess.run(predict_real, feed_dict={input: batch_input, target: batch_target})

運行的時候出現：{TypeError}unhashable type: 'numpy.ndarray'

后　　來　　發　　現：

在session外邊定義input和target的時候是這么寫的：

input = tf.placeholder(dtype=tf.float32, shape=[None, image_size, image_size, num_channels])
target = tf.placeholder(dtype=tf.float32, shape=[None, image_size, image_size, num_channels])

然而，我在開啟session后又定義了input，target。這導致我在運行下面這行代碼的時候，

sess.run(predict_real, feed_dict={input: batch_input, target: batch_target})

出現了{TypeError}unhashable type: 'numpy.ndarray'這樣的錯誤。然而此input和target非session外面的input和target。知道是這個原因后，改正的話就很簡單了，修改session內input和target的名稱即可，如下：

    with tf.Session() as sess:
        init = tf.global_variables_initializer()
        sess.run(init)
        if a.mode == 'train':
            for epoch in range(a.epochs):
                batch_input, batch_target = load_batch_data(a=a)
                batch_input = batch_input.astype(np.float32)
                batch_target = batch_target.astype(np.float32)
                sess.run(model, feed_dict={input: batch_input, target: batch_target})
                print('epoch' + str(epoch) + ':')
            saver.save(sess, 'model_parameter/train.ckpt')
            print('training finished!!!')
        elif a.mode == 'test':
            #ceshi
            ckpt = tf.train.latest_checkpoint(a.checkpoint)
            saver.restore(sess, ckpt)
            # 獲取測試時候的圖像，然后添加標簽
            batch_input, _ = load_batch_data(a=a)
            # batch_input = batch_input / 255.
            batch_input = batch_input.astype(np.float32)
            generator_output = sess.run(test_output, feed_dict={input: batch_input})
            # 對結果進行處理，圖像通道上減去3，得到rgb圖像
            result = process_generator_output(generator_output)
            if result:
                print('測試完成！')
        else:
            print('the MODE is not avaliable...')