max_segment_len = 20 #The max length of a segment in dataset is 114
min_word_frequency = 1
embedding_vecor_length = 300
use_pretrained_word_embedding = True
use_pretrained_single_model = True
use_cartesian_fusion = True
end_to_end = True
feature_selection = True
a, b = 4.0, 8.0
fusion_method = 'Cartesion' if use_cartesian_fusion else 'Concat'
#word2ix = loader.load_word2ix()
word_embedding = [loader.load_word_embedding()
] if use_pretrained_word_embedding else None
train, valid, test = loader.load_word_level_features(max_segment_len, tr_split)
feature_str = ''
if args.feature_selection:
with open('/media/bighdd5/Paul/mosi/fs_mask.pkl') as f:
[covarep_ix, facet_ix] = pickle.load(f)
facet_train = train['facet'][:, :, facet_ix]
facet_valid = valid['facet'][:, :, facet_ix]
facet_test = test['facet'][:, :, facet_ix]
covarep_train = train['covarep'][:, :, covarep_ix]
covarep_valid = valid['covarep'][:, :, covarep_ix]
covarep_test = test['covarep'][:, :, covarep_ix]
feature_str = '_t' + str(embedding_vecor_length) + '_c' + str(
covarep_test.shape[2]) + '_f' + str(facet_test.shape[2])
else:
facet_train = train['facet']
def get_data(args, config):
tr_split = 2.0 / 3 # fixed. 62 training & validation, 31 test
val_split = 0.1514 # fixed. 52 training 10 validation
use_pretrained_word_embedding = True # fixed. use glove 300d
embedding_vecor_length = 300 # fixed. use glove 300d
# 115 # fixed for MOSI. The max length of a segment in MOSI dataset is 114
max_segment_len = config['seqlength']
end_to_end = True # fixed
word2ix = loader.load_word2ix()
word_embedding = [loader.load_word_embedding()
] if use_pretrained_word_embedding else None
train, valid, test = loader.load_word_level_features(
max_segment_len, tr_split)
ix2word = inv_map = {v: k for k, v in word2ix.iteritems()}
print len(word2ix)
print len(ix2word)
print word_embedding[0].shape
feature_str = ''
if args.feature_selection:
with open('/media/bighdd5/Paul/mosi/fs_mask.pkl') as f:
[covarep_ix, facet_ix] = pickle.load(f)
facet_train = train['facet'][:, :, facet_ix]
facet_valid = valid['facet'][:, :, facet_ix]
facet_test = test['facet'][:, :, facet_ix]
covarep_train = train['covarep'][:, :, covarep_ix]
covarep_valid = valid['covarep'][:, :, covarep_ix]
covarep_test = test['covarep'][:, :, covarep_ix]
feature_str = '_t' + str(embedding_vecor_length) + '_c' + str(
covarep_test.shape[2]) + '_f' + str(facet_test.shape[2])
else:
facet_train = train['facet']
facet_valid = valid['facet']
covarep_train = train['covarep'][:, :, 1:35]
covarep_valid = valid['covarep'][:, :, 1:35]
facet_test = test['facet']
covarep_test = test['covarep'][:, :, 1:35]
text_train = train['text']
text_valid = valid['text']
text_test = test['text']
y_train = train['label']
y_valid = valid['label']
y_test = test['label']
lengths_train = train['lengths']
lengths_valid = valid['lengths']
lengths_test = test['lengths']
#f = h5py.File("out/mosi_lengths_test.hdf5", "w")
#f.create_dataset('d1',data=lengths_test)
#f.close()
#assert False
facet_train_max = np.max(np.max(np.abs(facet_train), axis=0), axis=0)
facet_train_max[facet_train_max == 0] = 1
#covarep_train_max = np.max(np.max(np.abs(covarep_train), axis =0),axis=0)
#covarep_train_max[covarep_train_max==0] = 1
facet_train = facet_train / facet_train_max
facet_valid = facet_valid / facet_train_max
#covarep_train = covarep_train / covarep_train_max
facet_test = facet_test / facet_train_max
#covarep_test = covarep_test / covarep_train_max
text_input = Input(shape=(max_segment_len, ),
dtype='int32',
name='text_input')
text_eb_layer = Embedding(word_embedding[0].shape[0],
embedding_vecor_length,
input_length=max_segment_len,
weights=word_embedding,
name='text_eb_layer',
trainable=False)(text_input)
model = Model(text_input, text_eb_layer)
text_train_emb = model.predict(text_train)
print text_train_emb.shape # n x seq x 300
print covarep_train.shape # n x seq x 5/34
print facet_train.shape # n x seq x 20/43
X_train = np.concatenate((text_train_emb, covarep_train, facet_train),
axis=2)
text_valid_emb = model.predict(text_valid)
print text_valid_emb.shape # n x seq x 300
print covarep_valid.shape # n x seq x 5/34
print facet_valid.shape # n x seq x 20/43
X_valid = np.concatenate((text_valid_emb, covarep_valid, facet_valid),
axis=2)
text_test_emb = model.predict(text_test)
print text_test_emb.shape # n x seq x 300
print covarep_test.shape # n x seq x 5/34
print facet_test.shape # n x seq x 20/43
X_test = np.concatenate((text_test_emb, covarep_test, facet_test), axis=2)
return X_train, y_train, X_valid, y_valid, X_test, y_test
