Tensorflow.js加载增强层操作出错

Question

我在 python 中通过 tensorflow 训练了一个模型，使用合并到模型层中的图像增强。但是，当我将训练好的模型转换为 tensorflow.js (model.json) 和运行时，出现错误：

jquery-3.3.1.slim.min.js:2 Uncaught Error: Unknown layer: RandomFlip. This may be due to one of the following reasons:
1. The layer is defined in Python, in which case it needs to be ported to TensorFlow.js or your JavaScript code.
2. The custom layer is defined in JavaScript, but is not registered properly with tf.serialization.registerClass().
    at jN (generic_utils.js:242)
    at GI (serialization.js:31)
    at e.fromConfig (models.js:1026)
    at jN (generic_utils.js:277)
    at GI (serialization.js:31)
    at e.fromConfig (models.js:1026)
    at jN (generic_utils.js:277)
    at GI (serialization.js:31)
    at models.js:295
    at u (runtime.js:45)

model.json 文件的内容如下： https://github.com/maximus3219/maximus3219.github.io/blob/main/Flower_model_EN0/model.json

这可能是由于扩充操作。我该如何处理这些问题？谢谢！

Answer 1

将 keras 模型转换为 tensorflow.js 格式时一定存在某种问题，因此像这样转换它会起作用

tensorflowjs_converter --input_format keras --output_format=tfjs_graph_model G:/Deep learning/test.h5 G:/Deep learning/Test/

Tensorflow.js加载增强层操作出错

Tensorflow.js error in loading augmentation layers operation

tensorflow

tensorflow.js