def build_pretrain_model(self, data_dict, hyper_params):
"""
pretrain-method specific;
constucts an SCE net;
works with any network structure of the pipeline
:param data_dict:
:param hyper_params:
:return:
"""
from theano import tensor
from blocks.model import Model
# Note: this has to match the sources defined in the dataset
indices = [tensor.ivector('{}_indices'.format(i)) for i in range(3)]
pipeline = self.encoder_pipeline_factory.build_pipeline(
input_shape=data_dict.get_value().shape, params=hyper_params)
# compute feature represenation
rep = [pipeline.apply(data_dict[indices[i]]) for i in range(3)]
# for r in rep: print r.type
# flatten representations
rep = [r.flatten(ndim=2) for r in rep]
# for r in rep: print r.type
# compute similarities
rval = []
for i in range(1, 3):
r = (rep[0] * rep[i]).sum(
axis=1) # element-wise multiplication and row sum
r = tensor.reshape(r, (r.shape[0], 1))
rval.append(r)
rval = tensor.concatenate(rval, axis=1)
# print rval.type
# optional softmax layer (normalization to sum = 1)
if 'apply_softmax' in hyper_params and hyper_params[
'apply_softmax']: # default=False
from blocks.bricks import Softmax
rval = Softmax().apply(rval)
# optional argmax (int output instead of scores
if 'return_probs' in hyper_params and hyper_params[
'return_probs'] is False: # default=True
rval = rval.argmax(axis=1)
return Model(rval)
