python - 如何将我自己的图像输入 Cifar10 训练模型并获得标签作为输出？

Question

我正在尝试使用基于 Cifar10 tutorial 的训练模型并且想喂它带有外部图像 32x32(jpg 或 png)。
我的目标是能够将标签作为输出。换句话说，我想为网络提供一个大小为 32 x 32、3 个 channel 且没有标签的 jpeg 图像作为输入，并让推理过程给我 tf.argmax (logits, 1).
基本上我希望能够在外部图像上使用经过训练的 cifar10 模型，看看它会吐出什么类。

我一直在尝试根据 Cifar10 教程来做这件事，不幸的是总是有问题。特别是 session 概念和批处理概念。

如能提供任何有关 Cifar10 的帮助，我们将不胜感激。

以下是到目前为止已实现的代码，但存在编译问题:

#!/usr/bin/env python

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

from datetime import datetime
import math
import time

import tensorflow.python.platform
from tensorflow.python.platform import gfile
import numpy as np
import tensorflow as tf

import cifar10
import cifar10_input
import os
import faultnet_flags
from PIL import Image

FLAGS = tf.app.flags.FLAGS

def evaluate():

  filename_queue = tf.train.string_input_producer(['/home/tensor/.../inputImage.jpg'])

  reader = tf.WholeFileReader()
  key, value = reader.read(filename_queue)

  input_img = tf.image.decode_jpeg(value)

  init_op = tf.initialize_all_variables()

# Problem in here with Graph / session
  with tf.Session() as sess:
    sess.run(init_op)

    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(coord=coord)

    for i in range(1): 
      image = input_img.eval()

    print(image.shape)
    Image.fromarray(np.asarray(image)).show()

# Problem in here is that I have only one image as input and have no label and would like to have
# it compatible with the Cifar10 network
    reshaped_image = tf.cast(image, tf.float32)
    height = FLAGS.resized_image_size
    width = FLAGS.resized_image_size
    resized_image = tf.image.resize_image_with_crop_or_pad(reshaped_image, width, height)
    float_image = tf.image.per_image_whitening(resized_image)  # reshaped_image
    num_preprocess_threads = 1
    images = tf.train.batch(
      [float_image],
      batch_size=128,
      num_threads=num_preprocess_threads,
      capacity=128)
    coord.request_stop()
    coord.join(threads)

    logits = faultnet.inference(images)

    # Calculate predictions.
    #top_k_predict_op = tf.argmax(logits, 1)

    # print('Current image is: ')
    # print(top_k_predict_op[0])

    # this does not work since there is a problem with the session
    # and the Graph conflicting
    my_classification = sess.run(tf.argmax(logits, 1))

    print ('Predicted ', my_classification[0], " for your input image.")


def main(argv=None):
  evaluate()

if __name__ == '__main__':
  tf.app.run() '''

Answer 1

首先是一些基础知识:

1. 首先定义图表:图像队列、图像预处理、convnet 推理、top-k 准确度
2. 然后创建一个 tf.Session() 并在其中工作:启动队列运行器，并调用 sess.run()

---

你的代码应该是这样的

# 1. GRAPH CREATION 
filename_queue = tf.train.string_input_producer(['/home/tensor/.../inputImage.jpg'])
...  # NO CREATION of a tf.Session here
float_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 SESSION
with 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，如果您只需要处理单个 图像，您可以删除队列运行器:

# 1. GRAPH CREATION
input_img = tf.image.decode_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 SESSION
with tf.Session() as sess:
  sess.run(init_op)

  top_indices = sess.run([top_k_pred])
  print ("Predicted ", top_indices[0], " for your input image.")