theano_rng = RandomStreams(numpy_rng.randint(2 ** 30))
cfg = pickle.load(smart_open(nnet_cfg,'rb'))
cfg.init_activation()
model = None
if cfg.model_type == 'DNN':
model = DNN(numpy_rng=numpy_rng, theano_rng = theano_rng, cfg = cfg)
elif cfg.model_type == 'CNN':
model = CNN(numpy_rng=numpy_rng, theano_rng = theano_rng, cfg = cfg, testing = True)
# load model parameters
_file2nnet(model.layers, path = nnet_param)
# initialize data reading
cfg.init_data_reading_test(data_spec)
model.dumpLayerSize()
# get the function for feature extraction
log('> ... getting the feat-extraction function for layer='+str(layer_index))
extract_func = model.build_extract_feat_function(layer_index)
output_mats = [] # store the features for all the data in memory. TODO: output the features in a streaming mode
log('> ... generating features from the specified layer')
while (not cfg.test_sets.is_finish()): # loop over the data
cfg.test_sets.load_next_partition(cfg.test_xy)
if batch_size == -1:
output = extract_func(cfg.test_x.get_value())
output_mats.append(output)
else:
batch_num = int(math.ceil(1.0 * cfg.test_sets.cur_frame_num / batch_size))
