如何用我自己的图像喂入Cifar10训练过的模型并获得标签作为输出？

首先要了解一些基础知识：

1. 首先定义图表：图像队列，图像预处理，卷积推理，top-k精度
2. 然后创建一个，

   tf.Session()

   并在其中进行操作：启动队列运行器，并调用

   sess.run()

这是您的代码应为的样子

# 1. GRAPH CREATION filename_queue = tf.train.string_input_producer(['/home/tensor/.../inputImage.jpg'])...  # NO CREATION of a tf.Session herefloat_image = ...images = tf.expand_dims(float_image, 0)  # create a fake batch of images (batch_size=1)logits = faultnet.inference(images)_, top_k_pred = tf.nn.top_k(logits, k=5)# 2. TENSORFLOW SESSIonwith tf.Session() as sess:    sess.run(init_op)    coord = tf.train.Coordinator()    threads = tf.train.start_queue_runners(coord=coord)    top_indices = sess.run([top_k_pred])    print ("Predicted ", top_indices[0], " for your input image.")

编辑：

正如@mrry所建议的，如果只需要处理 单个 图像，则可以删除队列运行器：

# 1. GRAPH CREATIONinput_img = tf.image.depre_jpeg(tf.read_file("/home/.../your_image.jpg"), channels=3)reshaped_image = tf.image.resize_image_with_crop_or_pad(tf.cast(input_img, width, height), tf.float32)float_image = tf.image.per_image_withening(reshaped_image)images = tf.expand_dims(float_image, 0)  # create a fake batch of images (batch_size = 1)logits = faultnet.inference(images)_, top_k_pred = tf.nn.top_k(logits, k=5)# 2. TENSORFLOW SESSIonwith tf.Session() as sess:  sess.run(init_op)  top_indices = sess.run([top_k_pred])  print ("Predicted ", top_indices[0], " for your input image.")