ValueError: Parent directory of model.ckpt doesn't exist, can't save.

描述：

tensorflow保存训练数据时报错：

ValueError: Parent directory of model.ckpt doesn't exist, can't save.

        #save model
        saver = tf.train.Saver({'W_conv1':W_conv1, 'b_conv1':b_conv1, 'W_conv2':W_conv2, 'b_conv2':b_conv2,
                                'W_fc1':W_fc1, 'b_fc1':b_fc1, 'W_fc2':W_fc2, 'b_fc2':b_fc2})
        saver.save(sess, "model.ckpt")
        #将训练好的模型保存为.pb文件
        output_graph_def = graph_util.convert_variables_to_constants(sess, sess.graph_def, output_node_names=['predict'])
        with tf.gfile.FastGFile('model.pb', mode='wb') as f:  # ’wb’中w代表写文件，b代表将数据以二进制方式写入文件。
            f.write(output_graph_def.SerializeToString())

解决办法：

将

saver.save(sess, "model.ckpt")

改为

saver.save(sess, "./model.ckpt")

即将路径改为相对路径