-
Notifications
You must be signed in to change notification settings - Fork 17
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
word2vec / universal sentence encoder example? #18
Comments
Maybe I can help to fix it. At which stage are you stuck? Please add error messages if that's the case. |
@bytosaur thanks. Actually I am stuck at an very early stage, it crashes when I try to run the model (I expected to get the tensor of the string):
I have to admit that my approach is very naive, and maybe you can point to a tutorial for understanding tensorflow/word2vec basics better? |
hey @Jonathhhan, could you please provide the error message as well? or is it just a seg fault? also which line throws the error? I have never worked with word embeddings before, but i think your understanding is correct. The text gets transformed into an n-dimensional vector which can be used for comparison. Usually these embeddings are used as a first step in language models to have a latent representation of the text. |
@bytosaur it crashes at
|
If I load the universal sentence encoder model https://tfhub.dev/google/universal-sentence-encoder/4 instead, I get a lot of information with
|
Actually there is a warning if I run the universal sentence encoder model (happens with other text models too):
This is basically what I would like with ofxTensoflow2: https://www.youtube.com/watch?v=YjRhIpfz5ms |
I made a universal sentence encoder example: https://github.com/Jonathhhan/ofxTensorFlow2/tree/universal-sentence-encoder/example_universal_sentence_encoder |
I updated the example, its a basic version of my "Montageautomat": https://github.com/Jonathhhan/ofxTensorFlow2/tree/universal-sentence-encoder/example_universal_sentence_encoder_video_2 |
I wonder if somebody use a word2vec model with ofxTensorflow2?
I found a model and tried to use it, but without success: https://tfhub.dev/google/Wiki-words-250-with-normalization/2
For now I use ofxWord2vec https://github.com/perevalovds/ofxWord2Vec for finding subtitle similarities (with a pretrained model) and I would like to do that with ofxTensorflow2 too...
https://github.com/Jonathhhan/ofEmscriptenExamples/tree/main/montageautomat_threaded_2
The text was updated successfully, but these errors were encountered: