How to convert the model trained by unsupervised learning (such as kmeans) with tensorflow lite?

TensorFlow General Discussion
,
1

Can I use tensorflow lite to convert the model trained by unsupervised learning (such as kmeans)?How to achieve it ? Thanks!

3

Hi,

Was your kmeans model trained using TensorFlow?
if so, you can try the TFLite converter: TensorFlow Lite 轉換工具

5

In other words, the tensorflow lite converter supports the conversion of kmeans models? I will try it, thank you!

7

No, it will support the conversion of TF models. So just in the case you have a TF kmeans implementation.

1 Like
9

I am a beginner, and the question may be a bit stupid.
If I use the xxd tool to convert this model into a hexadecimal vector format, as shown below, how should I use it and what does the number in this vector represent?

unsigned char converted_model_tflite[] = {  0x18, 0x00, 0x00, 0x00, 0x54, 0x46, 0x4c, 0x33, 0x00, 0x00, 0x0e, 0x00,  // <Lines omitted>};unsigned int converted_model_tflite_len = 18200;