How to train from sequences of features instead of sentences

I want to train a model from sequences of features instead of sentences. The feature is various, so I can not make a dictionary for sequences of features as sentences. Can any one help me?

Can you be more specific about the kind of features you want to use? Are they just continuous vectors?

Hi guilaume Klein
Yes, they are continuous vectors. One example of input is a sequence of point in online handwritten. But we also extract more features, so the input is a sequence of real number vector as follows
[v1, v2, v3, …, vn]
[c1, c2, c3 … cm]
where vi is a vector of real number and cj is a character in ground truth of handwritten.

Thanks for your consideration

This has been applied in:


Currently this requires a bit of coding to change the data loading part and give your own ìnputNetwork that fits your application:

Thanks for your suggestions. I used Im2Text to recognize images of handwritten, but I want recognize online handwritten (recognize from sequences of points ). I will try the second one that you suggested.
Thanks for your quick response.

Hi @tintinkool - as mentioned by @guillaumekln - the feature is already available in some branches, I will prepare a PR to get it available on the master. keep tuned.

Thank @jean.senellart and @guillaumekln for helping. Could you give me files in your example in topic "[WIP] Complex Encoders and vector inputs (used for ASR) "?
I will try to use this feature.


Hi @tintinkool - the code is available in the PR - I am preparing short training example and will write a tutorial this week before merging.