如何将jpeg数据加载，标记和提供给Tensorflow？ [英] How do you load, label, and feed jpeg data into Tensorflow?

问题描述

我一直在尝试将1750 * 1750图像输入Tensorflow，但在使用tf.image.decode_jpeg（）函数将图像转换为Tensor后，我不知道如何标记和提供数据。

I have been trying to feed 1750 * 1750 images into Tensorflow, but I do not know how to label and feed the data after I convert the images into a Tensor using the tf.image.decode_jpeg() function.

目前，我的代码是：

import tensorflow as tf
import numpy as np

import imageflow
import os, glob

sess = tf.InteractiveSession()

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

 my_img = tf.image.decode_jpeg(value)
 my_img.set_shape([1750, 1750, 1])
 print(value)
 return my_img

#####################################################
def read_image_data():
 jpeg_files = []
 images_tensor = []

 i = 1
 WORKING_PATH = "/Users/Zanhuang/Desktop/NNP/DATA"
 jpeg_files_path = glob.glob(os.path.join(WORKING_PATH, '*.jpeg'))

 for filename in jpeg_files_path:
    print(i)
    i += 1
    jpeg_files.append(filename)


 filename_queue = tf.train.string_input_producer(jpeg_files)

 mlist = [read_jpeg(filename_queue) for _ in range(len(jpeg_files))]

 init = tf.initialize_all_variables()

 sess = tf.Session()
 sess.run(init)

 images_tensor = tf.convert_to_tensor(images_tensor)


 sess.close()

现在，正如我之前所说，我需要输入和标记数据。我已经看过CIFAR-10教程文件，但是他们将标签存储在一个文件中，我打算不这样做。

Now, as I said earlier, I need to feed and label the data. I have seen the CIFAR-10 tutorial files, but they stored the labels in a file and I plan on not doing that way.

我对Tensorflow很新，所以请保持尽可能详细的回复。

I am quite new to Tensorflow so please keep the response as detailed as possible.

谢谢！

推荐答案

根据您的目的，有几个方向需要考虑。

Depending on what you are trying to do, there are several directions to consider.

1. 如果您只是希望对任意JPEG文件（即不需要标签），然后你可以按照classify_image.py的例子，它将JPEG图像输入预先训练好的Inception网络：

1. If you just wish to run inference on an arbitrary JPEG file (i.e. labels are not required), then you can follow the example of classify_image.py which feeds in a JPEG image into a pre-trained Inception network:

github.com/tensorflow/models/blob/master/ tutorials / image / imagenet / classify_image.py

如果您希望在上训练（或微调）模型小的自定义JPEG图像数据集，然后看看这个关于如何从一小组JPEG图像中训练模型的示例。

If you do wish to train (or fine-tune) a model on a small custom data set of JPEG images, then take a look at this example for how to train a model off a small set of JPEG images.

github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/image_retraining/retrain.py

如果您希望在大型自定义JPEG图像数据集上训练（或微调）模型，那么读取许多单独的JPEG文件将效率低下，培训速度极慢。

If you do wish to train (or fine-tune) a model on a large custom data set of JPEG images, then reading many individual JPEG files will be inefficient and slow down training tremendously.

我建议按照初始/模型库中描述的程序进行操作将JPEG图像目录转换为包含序列化JPEG图像的分片RecordIO。

I would suggest following the procedure of described in the inception/ model library that converts a directory of JPEG images into sharded RecordIO containing serialized JPEG images.

github.com/tensorflow/models/blob/master/research/inception/inception/data/build_im age_data.py

此处提供了运行转换脚本的说明：

Instructions for running the conversion script are available here:

github .com / tensorflow / models / blob / master / research / inception / README.md＃how-to-construct-a-new-dataset-for-retraining

运行转换后，您可以使用/复制初始/模型使用的图像预处理管道。

After running the conversion, you may then employ/copy the image preprocessing pipeline used by the inception/ model.

github.com/tensorflow/models/blob/master/research/inception/inception/image_processing.py

这篇关于如何将jpeg数据加载，标记和提供给Tensorflow？的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！