chars2vec

chars2vec copied to clipboard

I quite new to this field and I just read the source code, but I am quite confused a little bit with the actual role `self.model` the Chars2Vec class. Can...

buiminhhien2k

I think there is some part of the Chars2Vec can be optimized with the new method "featuring_word". I also create a new method call "check_similarity" to check the similarity of...

buiminhhien2k

Begging for the training data

7

LuMelon

See commit messages for list of hotfixes and changes. Closes PR #8

ZaxR

not able to reproduce the training procedure

4

I referred to the website where I found a piece of code to reproduce training of Char2Vec but it produces an error, can you please help. If it works I...

ShrikanthSingh

Triplet Loss

1

Just a query, have you tried triplet loss or lossless triplet loss as I think that would produce better embeddings as we are providing fewer examples and the clusters formed...

halloTheCoder

I tried to install chars2vec by pip: ``` pip3 install chars2vec ``` But It shows ``` error: can't copy 'chars2vec/trained_models/eng_200': doesn't exist or not a regular file ``` Does anyone...

louchenyao

Using vectorize_words leads to AttributeError

3

Hello, I am using keras ==2.9.0 and tensorflow ==2.9.1. I'm using pretrained eng_50 model like so -- `c2v_model = chars2vec.load_model('eng_50') ` However, when I use the vectorize_words method on my...

gabecano4308

sunilnitdgp

I've only seen the training example with which we can create a new model from scratch with our training data. What if we wanted to make one of the pretrained...

gab-palmeri