TensorFlow：用我自己的图像训练 [英] TensorFlow: training on my own image

问题描述

我是TensorFlow的新手。我正在寻找有关图像识别的帮助，可以在其中训练自己的图像数据集。

I am new to TensorFlow. I am looking for the help on the image recognition where I can train my own image dataset.

是否有用于训练新数据集的示例？ ？

Is there any example for training the new dataset?

推荐答案

如果您对如何在TensorFlow中输入自己的数据感兴趣，可以查看本教程。

我还为斯坦福大学CS230编写了最佳实践指南< a href = https://cs230-stanford.github.io/tensorflow-input-data.html#building-an-image-data-pipeline rel = noreferrer>此处。

If you are interested in how to input your own data in TensorFlow, you can look at this tutorial.
I've also written a guide with best practices for CS230 at Stanford here.

在 r1.4 中引入了 tf.data 之后，我们可以创建一批没有占位符且没有队列的图像。步骤如下：

With the introduction of tf.data in r1.4, we can create a batch of images without placeholders and without queues. The steps are the following:

1. 创建一个包含图像文件名和标签列表的列表


2. 创建一个 tf.data.Dataset 读取这些文件名和标签


3. 预处理数据


4. 从 tf.data.Dataset 创建一个迭代器，该迭代器将产生下一批

1. Create a list containing the filenames of the images and a corresponding list of labels
2. Create a tf.data.Dataset reading these filenames and labels
3. Preprocess the data
4. Create an iterator from the tf.data.Dataset which will yield the next batch

代码为：

# step 1
filenames = tf.constant(['im_01.jpg', 'im_02.jpg', 'im_03.jpg', 'im_04.jpg'])
labels = tf.constant([0, 1, 0, 1])

# step 2: create a dataset returning slices of `filenames`
dataset = tf.data.Dataset.from_tensor_slices((filenames, labels))

# step 3: parse every image in the dataset using `map`
def _parse_function(filename, label):
    image_string = tf.read_file(filename)
    image_decoded = tf.image.decode_jpeg(image_string, channels=3)
    image = tf.cast(image_decoded, tf.float32)
    return image, label

dataset = dataset.map(_parse_function)
dataset = dataset.batch(2)

# step 4: create iterator and final input tensor
iterator = dataset.make_one_shot_iterator()
images, labels = iterator.get_next()

现在我们可以直接运行 sess.run（[图像，标签]），而无需通过占位符提供任何数据。

Now we can run directly sess.run([images, labels]) without feeding any data through placeholders.

总而言之，您可以执行多个步骤：

To sum it up you have multiple steps:

1. 创建文件名列表（例如：图像的路径）


2. 创建TensorFlow 文件名队列


3. 读取并解码每个图像，将它们调整为固定大小（对于批处理而言是必需的）


4. 输出一批这些图像

1. Create a list of filenames (ex: the paths to your images)
2. Create a TensorFlow filename queue
3. Read and decode each image, resize them to a fixed size (necessary for batching)
4. Output a batch of these images

---

最简单的代码是：

---

The simplest code would be:

# step 1
filenames = ['im_01.jpg', 'im_02.jpg', 'im_03.jpg', 'im_04.jpg']

# step 2
filename_queue = tf.train.string_input_producer(filenames)

# step 3: read, decode and resize images
reader = tf.WholeFileReader()
filename, content = reader.read(filename_queue)
image = tf.image.decode_jpeg(content, channels=3)
image = tf.cast(image, tf.float32)
resized_image = tf.image.resize_images(image, [224, 224])

# step 4: Batching
image_batch = tf.train.batch([resized_image], batch_size=8)

这篇关于TensorFlow：用我自己的图像训练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！