[英]How to use tensorflow model for predicting my own images
I've just started with tensorflow.我刚刚开始使用 tensorflow。 I wrote a program that uses Fashion_MNIST dataset to train the model.
我编写了一个程序,使用 Fashion_MNIST 数据集来训练 model。 And then predicts the labels using 'test_images'and it's working good so far.
然后使用“test_images”预测标签,到目前为止效果很好。 But what I am curious how can I use my own image of a shoe or shirt for prediction.
但是我很好奇如何使用自己的鞋子或衬衫图像进行预测。 Because all the test images are of shape 28*28.
因为所有测试图像的形状都是 28*28。 How can I do this?
我怎样才能做到这一点?
The task you are engaged in is the task of data preparation and preprocessing.你所从事的任务是数据准备和预处理的任务。 Among the things you must do already having a directory with images is the tagging of the images, for this task I recommend labelImg .
已经拥有一个包含图像的目录必须做的事情之一是标记图像,对于这个任务,我推荐labelImg 。 If you also need the dimensionality of the input to be of a specific size like the example you give, you can use digital image processing software.
如果您还需要输入的维度具有特定大小,就像您给出的示例一样,您可以使用数字图像处理软件。 The OpenCV library has dimensionality reduction tools that work for this.
OpenCV库具有适用于此的降维工具。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.