PROSAGA码农传奇-深度学习-如何调整图像大小以放入tf.train.Example

如何调整图像大小以放入tf.train.Example

作者: Mystery☀
发布时间: 2025-02-14 02:50:02 (7天前)
转自：

<div class =“post-text”itemprop =“text”>
  <P>
    您可以在编码之前调整大小。
  </p>
   <pre>
    <code>
      def int64_feature(value):
    return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))

def bytes_feature(value):
    return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))

</code>
  </pre>
  <P>
    从字符串转换并调整大小
  </p>
   <pre>
    <code>
      image = numpy.fromstring(byte_arr).reshape((height, width, channels))
image_raw = image.tostring()

</code>
  </pre>
  <P>
    然后序列化为tfrecords文件
  </p>
   <pre>
    <code>
      writer = tf.python_io.TFRecordWriter(tfr_name)
example = tf.train.Example(features=tf.train.Features(feature{'height':int64_feature(height),
                                                              'width': int64_feature(width),
                                                              'channels': int64_feature(channels),
                                                              'image_raw': bytes_feature(image_raw),

writer.write(example.SerializeToString())
writer.close()

</code>
  </pre>
</DIV>