DeepLearning4j - INDArray 转为图像

最新推荐文章于 2024-12-01 23:12:52 发布

寒沧

最新推荐文章于 2024-12-01 23:12:52 发布

阅读量1.5k

点赞数 1

分类专栏： deeplearning4j DeepLearning4j

本文链接：https://blog.csdn.net/u011669700/article/details/86370491

版权

本文介绍了如何使用DeepLearning4j库将INDArray转换为图像，涵盖了三通通道彩色图和单通道灰度图的处理。通过Java2DNativeImageLoader进行图像加载，并展示了如何将处理后的图像保存到本地。提供了相关代码示例和官方文档链接，便于读者实践。

摘要由CSDN通过智能技术生成

三通通道彩色图

代码引自：https://github.com/sjsdfg/dl4j-tutorials/blob/master/src/main/java/styletransfer/NeuralStyleTransfer.java

 /**
 * Takes an INDArray containing an image loaded using the native image loader
 * libraries associated with DL4J, and converts it into a BufferedImage.
 * The INDArray contains the color values split up across three channels (RGB)
 * and in the integer range 0-255.
 *
 * @param array INDArray containing an image
 * @return BufferedImage
 */
private BufferedImage imageFromINDArray(INDArray array) {
   
    long[] shape = array.shape();

    long height = shape[2];
    long width = shape[3];
    BufferedImage image = new BufferedImage((int)width, (int)height, BufferedImage.TYPE_INT_RGB);
    for (int x = 0; x < width; x++) {
   
        for (int y = 0; y < height; y