yoctol / seq2vec Goto Github PK

View Code? Open in Web Editor NEW

68.0 15.0 8.0 1.67 MB

Transform sequence of words into a fix-length representation vector

License: GNU General Public License v3.0

Python 100.00%

keras seq2vec-model

seq2vec's Issues

model cannot be picklized

Seq2SeqAutoEncoderUseWordHash cannot be picklized.

requirement

不知道要不要多加
tensorflow-gpu ??
(如果同時pip install tensorflow 和 tensorflow-gpu 不知道會發生什麼事情？？）

version in requirements.txt

Hi,
can you kindly update the requirements.txt file with the correct version of all modules?
Thanks a lot

Use consistent hash

from sklearn.utils import murmurhash3_32

murmurhash3_32('a', seed=0)

can't load word2vec model when running example code

I am trying to execute the LSTM to LSTM auto-encoder with word embedding (RNN to RNN architecture) example. I have already trained my own word2vec model via gensim and saved it with the command
model.save('/home/estathop/Documents/word2vecmodel/w2v1model') #save model
when trying to use the

# load Gensim word2vec from word2vec_model_path
word2vec = GensimWord2vec('/home/estathop/Documents/word2vecmodel/w2v1model')

the following error occurs:

Traceback (most recent call last):

File "", line 5, in
word2vec = GensimWord2vec('/home/estathop/Documents/word2vecmodel/w2v1model')

File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/seq2vec/word2vec/gensim_word2vec.py", line 9, in init
model_path, binary=True

File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/gensim/models/keyedvectors.py", line 1120, in load_word2vec_format
limit=limit, datatype=datatype)

File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/gensim/models/utils_any2vec.py", line 174, in _load_word2vec_format
header = utils.to_unicode(fin.readline(), encoding=encoding)

File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/gensim/utils.py", line 359, in any2unicode
return unicode(text, encoding, errors=errors)

File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/encodings/utf_8.py", line 16, in decode
return codecs.utf_8_decode(input, errors, True)

UnicodeDecodeError: 'utf8' codec can't decode byte 0x80 in position 0: invalid start byte

any ideas how to fix/bypass this ?

fix version of library to be installed

move ci from circle_ci to travis_ci ???

Not a single example in README is running properly.

I tried to execute every single example from the initial README page, but everything throws different errors.

transformer = Seq2VecR2RWord(
    word2vec_model=word2vec,
    max_length=max_length,
    latent_size=200,
    encoding_size=300,
    learning_rate=0.05
)
Traceback (most recent call last):

  File "<ipython-input-42-34cf056a2e62>", line 6, in <module>
    learning_rate=0.05

  File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/seq2vec/model/seq2vec_R2R_word.py", line 55, in __init__
    learning_rate=learning_rate

  File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/seq2vec/model/seq2vec_base.py", line 68, in __init__
    self.model, self.encoder = self.create_model()

  File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/seq2vec/model/seq2vec_R2R_word.py", line 89, in create_model
    )(masked_inputs)

  File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/keras/layers/wrappers.py", line 325, in __call__
    return super(Bidirectional, self).__call__(inputs, **kwargs)

  File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/keras/engine/topology.py", line 619, in __call__
    output = self.call(inputs, **kwargs)

  File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/yklz/recurrent/bidirectional_rnn_encoder.py", line 31, in call
    func_args = inspect.getfullargspec(self.layer.call).args

AttributeError: 'module' object has no attribute 'getfullargspec'

from seq2vec import Seq2VecR2RHash

transformer = Seq2VecR2RHash(
    max_index=1000,
    max_length=10,
    latent_size=20,
    embedding_size=200,
    encoding_size=300,
    learning_rate=0.05
)

Traceback (most recent call last):

  File "<ipython-input-38-0274b84666d1>", line 9, in <module>
    learning_rate=0.05

  File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/seq2vec/model/seq2vec_R2R_hash.py", line 58, in __init__
    learning_rate

  File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/seq2vec/model/seq2vec_base.py", line 68, in __init__
    self.model, self.encoder = self.create_model()

  File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/seq2vec/model/seq2vec_R2R_hash.py", line 96, in create_model
    )(char_embedding)

  File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/keras/layers/wrappers.py", line 325, in __call__
    return super(Bidirectional, self).__call__(inputs, **kwargs)

  File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/keras/engine/topology.py", line 619, in __call__
    output = self.call(inputs, **kwargs)

  File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/yklz/recurrent/bidirectional_rnn_encoder.py", line 31, in call
    func_args = inspect.getfullargspec(self.layer.call).args

AttributeError: 'module' object has no attribute 'getfullargspec'

In [37]: transformer = Seq2VecC2RChar(
      word2vec_model=word2vec,
      max_index=1000,
      max_length=20,
      embedding_size=200,
      latent_size=200,
      learning_rate=0.05,
      channel_size=10,
      conv_size=5
)

Traceback (most recent call last):

  File "<ipython-input-37-1396dd8326f9>", line 9, in <module>
    conv_size=5

  File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/seq2vec/model/seq2vec_C2R_char.py", line 69, in __init__
    learning_rate

  File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/seq2vec/model/seq2vec_base.py", line 68, in __init__
    self.model, self.encoder = self.create_model()

  File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/seq2vec/model/seq2vec_C2R_char.py", line 153, in create_model
    )(encoded_feature)

  File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/keras/engine/topology.py", line 619, in __call__
    output = self.call(inputs, **kwargs)

  File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/yklz/recurrent/rnn_decoder.py", line 95, in call
    constants = self.layer.get_constants(inputs, training=None)

  File "/home/estathop/anaconda2/envs/tensorflow/lib/python2.7/site-packages/yklz/recurrent/rnn_cell.py", line 277, in get_constants
    constants = self.recurrent_layer.get_constants(

AttributeError: 'LSTM' object has no attribute 'get_constants'

Need new release !!!

modified readme
Since the version on pip is 0.6.0, but the released version is 0.4.0.
New new pip version and new release for fixed keras version.

how to train it from scratch?

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.