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()
initialDim = model.getNeuronsForLayer(i)
for p in perplexity:
files.append(createDataFile(output_path,'Layer'+str(layer_index),countItems,2,initialDim,p))
# get the function for feature extraction
log('> ... getting the feat-extraction function')
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)
batch_num = int(math.ceil(1.0 * cfg.test_sets.cur_frame_num / batch_size))
for batch_index in range(batch_num): # loop over mini-batches
start_index = int(batch_index * batch_size)
