jonzarecki/lstm-sentence-similarity

Theano implementation of siamese LSTMs for evaluating semantic similarity between sentences.

lstm-sentence-similarity's Issues

failed in download!!! how to download? Can you provide a link?

Download the word2vec model from https://code.google.com/archive/p/word2vec/

About saving model

your model saves training results using example3.py
but unfortunately, when it reloads the saved pickle file it doesnot execute like it does for bestsem.p
it could not find keys() . kindly help me in this regard that how may i save the newly learnt weights

You can make a video tutorial on running the code. I hope you do it on youtube. thank you

python version ???
library sets: tensorflow version ??, gensim version ??, vvv ...
You can make a video tutorial on running the code. I hope you do it on youtube. thank you

problem when lstm constructor loads

hello!
while trying to start training .getting this error

pdb> > /home/seemab/seemab/Siamese-LSTM-master/lstmQA.py(191)adadelta()
189 for rg2, g in zip(running_grads2, grads)]
190
7-> 191 f_grad_shared = theano.function([emb11,mask11,emb21,mask21,y], cost, updates=zgup + rg2up,
192 name='adadelta_f_grad_shared',allow_input_downcast=True)
193

ipdb>
ipdb> Traceback (most recent call last):

File "", line 1, in
debugfile('/home/seemab/seemab/Siamese-LSTM-master/trainQA.py', wdir='/home/seemab/seemab/Siamese-LSTM-master')

File "/home/seemab/.local/lib/python2.7/site-packages/spyder/utils/site/sitecustomize.py", line 728, in debugfile
debugger.run("runfile(%r, args=%r, wdir=%r)" % (filename, args, wdir))

File "/home/seemab/anaconda2/lib/python2.7/bdb.py", line 400, in run
exec cmd in globals, locals

File "", line 1, in

File "/home/seemab/.local/lib/python2.7/site-packages/spyder/utils/site/sitecustomize.py", line 705, in runfile
execfile(filename, namespace)

File "/home/seemab/.local/lib/python2.7/site-packages/spyder/utils/site/sitecustomize.py", line 94, in execfile
builtins.execfile(filename, *where)

File "/home/seemab/seemab/Siamese-LSTM-master/trainQA.py", line 14, in
sls=lstm("new.p",load=False,training=True) #call to class lstm()

File "lstmQA.py", line 303, in init
self.f_grad_shared, self.f_update = adadelta(lr, tnewp, grads,emb11,mask11,emb21,mask21,y, cost)

File "lstmQA.py", line 192, in adadelta
name='adadelta_f_grad_shared',allow_input_downcast=True)

File "/home/seemab/anaconda2/lib/python2.7/site-packages/theano/compile/function.py", line 298, in function
output_keys=output_keys)

File "/home/seemab/anaconda2/lib/python2.7/site-packages/theano/compile/pfunc.py", line 449, in pfunc
no_default_updates=no_default_updates)

File "/home/seemab/anaconda2/lib/python2.7/site-packages/theano/compile/pfunc.py", line 208, in rebuild_collect_shared
raise TypeError(err_msg, err_sug)

TypeError: ('An update must have the same type as the original shared variable (shared_var=1lstm1_U_rgrad2, shared_var.type=TensorType(float32, matrix), update_val=Elemwise{add,no_inplace}.0, update_val.type=TensorType(float64, matrix)).', 'If the difference is related to the broadcast pattern, you can call the tensor.unbroadcast(var, axis_to_unbroadcast[, ...]) function to remove broadcastable dimensions.')