skip-thoughts
skip-thoughts copied to clipboard
KeyError in decoding
Upon running the load_model function in the decoding package with both the uni_skip and bi_skip models provided, I get the following error:
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "tools.py", line 47, in load_model
params = init_params(options)
File "model.py", line 27, in init_params
params = get_layer('ff')[0](options, params, prefix='ff_state', nin=options['dimctx'], nout=options['dim'])
KeyError: 'dimctx'
Even after I attempt to hard code the value of dimctx, the gru_cond_simple throws a similar error.
@shavakagrawal Were you able to run the decoder? I am also facing the same error!
I found an interface for skip-thought vectors here, but now the memory requirement seems to be a major issue. Can you help me with how much RAM is required for the decoder on ~10000 sentences, if you were able to run the decoder? Thanks!
Nope, ended up retraining on my corpus