junfenglx / reasoning_attention Goto Github PK

where did you use word2vector?Out-of-vocabulary words on the test corpus are set to fixed random vectors in the paper.but, in the"snli_match_lstm_predict.py",you use "print('Warning: {} not in dictionary'.format(w))" to handle the oov.why?

Hi, I am not able to run the command

python ./snli_match_lstm.py

I created a python3.5 environment with anaconda, where I installed the Bleeding-edge version of Theano/Lasagne with

pip install --upgrade https://github.com/Theano/Theano/archive/master.zip
pip install --upgrade https://github.com/Lasagne/Lasagne/archive/master.zip

The following error message is depicted:

(py35)user1@machine:~/matchLSTM$ python ./snli_match_lstm.py
Loading data ...
Loading train ...
550152
550149
549364
Loading dev ...
10000
10000
9842
Loading test ...
10000
10000
9824
num_epochs: 20
k: 300
batch_size: 30
display_frequency: 100
save_frequency: 1000
load previous: False
Building network ...
unchanged_W.shape: (34283, 300)
oov_in_train_W.shape: (9166, 300)
apply dropout mask id 140482817419472 to embedding matrix ...
dropout rate is 0.3
input var is hypo_var
apply dropout mask id 140482817419472 to embedding matrix ...
dropout rate is 0.3
input var is premise_var
Computing updates ...
Compiling functions ...
Traceback (most recent call last):
File "/home/user1/anaconda2/envs/py35/lib/python3.5/site-packages/theano/compile/pfunc.py", line 193, in rebuild_collect_shared
allow_convert=False)
File "/home/user1/anaconda2/envs/py35/lib/python3.5/site-packages/theano/tensor/type.py", line 234, in filter_variable
self=self))
TypeError: Cannot convert Type TensorType(float64, matrix) (of Variable Elemwise{add,no_inplace}.0) into Type TensorType(float32, matrix). You can try to manually convert Elemwise{add,no_inplace}.0 into a TensorType(float32, matrix).

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "./snli_match_lstm.py", line 325, in
main(num_epochs=20, batch_size=30, load_previous=False)
File "./snli_match_lstm.py", line 213, in main
cost, updates=updates)
File "/home/user1/anaconda2/envs/py35/lib/python3.5/site-packages/theano/compile/function.py", line 326, in function
output_keys=output_keys)
File "/home/user1/anaconda2/envs/py35/lib/python3.5/site-packages/theano/compile/pfunc.py", line 447, in pfunc
no_default_updates=no_default_updates)
File "/home/user1/anaconda2/envs/py35/lib/python3.5/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=<TensorType(float32, matrix)>, 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.')

END OR ERROR MESSAGE