def train(args):
full = True if args.full == 'true' else False
# get data
if(args.grocery == 'false'):
X_train, Y_train = load_h5(args.train)
X_val, Y_val = load_h5(args.val)
else:
X_train = pickle.load(open("../data/grocery/grocery/grocery-train-data" + args.train))
Y_train = pickle.load(open("../data/grocery/grocery/grocery-train-label" + args.train))
X_val = pickle.load(open("../data/grocery/grocery/grocery-test-data_" + args.train))
Y_val = pickle.load(open("../data/grocery/grocery/grocery-test-label" + args.train))
X_train = np.reshape(X_train, [X_train.shape[0], X_train.shape[1], 1])
Y_train = np.reshape(Y_train, [Y_train.shape[0], Y_train.shape[1], 1])
X_val = np.reshape(X_val, [X_val.shape[0], X_val.shape[1], 1])
Y_val = np.reshape(Y_val, [Y_val.shape[0], Y_val.shape[1], 1])
# reshape piano data
if args.piano == 'true':
X_train = np.reshape(X_train, [X_train.shape[0], X_val.shape[2], X_val.shape[1]])
Y_train = np.reshape(Y_train, [Y_train.shape[0], Y_val.shape[2], Y_val.shape[1]])
X_val = np.reshape(X_val, [X_val.shape[0], X_val.shape[2], X_val.shape[1]])
Y_val = np.reshape(Y_val, [Y_val.shape[0], Y_val.shape[2], Y_val.shape[1]])
# determine super-resolution level
print(Y_train[0].shape)
print(Y_train[0])
n_dim, n_chan = Y_train[0].shape
r = Y_train[0].shape[1] / X_train[0].shape[1]
assert n_chan == 1
# Train seq2seq model
if(args.model == 'seq2seq'):
model = models.Model2()
model.run(X_train, Y_train, X_val, Y_val, n_epoch=args.epochs, r=args.r, speaker=args.speaker, grocery=args.grocery)
else:
# create model
model = get_model(args, n_dim, r, from_ckpt=False, train=True)
# train model
model.fit(X_train, Y_train, X_val, Y_val, n_epoch=args.epochs, r=args.r, speaker=args.speaker, grocery=args.grocery, piano=args.piano, calc_full_snr = full)
MAX_NB_SENSES = max([len(LEMMA2SENSES[k]) for k in LEMMA2SENSES
]) # max number of senses among all target words
MAX_NB_TARGETS = len(LEMMA2SENSES) # how many target words
# load word embedding initialized by init_emb (run init_emb first if you don't have this file)
with open('pretrained_vectors/needed' + '.pkl', 'rb') as f:
WORD_VECTORS = pickle.load(f)
WORD_VECTORS["_drop_"] = np.random.uniform(
-0.1, 0.1, 300) # add drop vector for drop words
NB_EPOCHS = 100 # number of epochs to train
x_val, y_val, _ = read_data.read_test_data(
LEMMA2INT, LEMMA2SENSES, WORD_VECTORS) # read validation data
"""train models"""
tf.reset_default_graph()
train_model = models.Model2(MAX_NB_SENSES, 32, MAX_NB_TARGETS)
val_model = models.Model2(MAX_NB_SENSES,
32,
MAX_NB_TARGETS,
is_training=False)
print("train models created")
"""run train models"""
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
VAL_ACC_LIST = []
LOSS_LIST = []
TRAIN_ACC_LIST = []
start0 = time.time()
saver = tf.train.Saver()
for nb_epoch in range(NB_EPOCHS):