def train_input():
X_train, Y_train = read_data.read_train_data()
Y_train = np.expand_dims(Y_train, axis=-1)
return X_train, Y_train
import tensorflow as tf
from tensorflow._api.v1.keras import layers
import read_data
x_train, y_train = read_data.read_train_data()
x_test, y_test = read_data.read_test_data()
num, H, W, _ = x_train.shape
model = tf.keras.models.Sequential([
tf.keras.layers.Conv2D(filters=16,
kernel_size=3,
strides=(1, 1),
padding='valid',
data_format='channels_last',
activation='relu',
use_bias=True,
input_shape=(H, W, 1)),
tf.keras.layers.Conv2D(filters=32,
kernel_size=3,
strides=(1, 1),
padding='same',
data_format='channels_last',
activation='relu',
use_bias=True,
input_shape=(H - 2, W - 2, 16)),
tf.keras.layers.Conv2D(filters=64,
kernel_size=3,
strides=(1, 1),
padding='same',
data_format='channels_last',
activation='relu',
import random
import csv
"""
This file is to plot the relationship between k and prediciton:
"""
def distance(data1, data2):
sum = 0.
for i in range(len(data1)):
sum += math.pow(data1[i] - data2[i], 2)
return math.sqrt(sum)
# read data:
data, train_data, validation_data, test_data, y, y_train, y_validation, y_test = read_data.read_train_data(
)
res = []
train_data_sample = []
y_train_sample = []
# read data from csv files:
with open('model_data.csv', newline='') as csvfile:
reader = csv.reader(csvfile, delimiter=" ", quotechar='|')
for row in reader:
train_data_sample.append((list(map(int, row[0].split(',')))))
with open('model_label.csv', newline='') as csvfile:
reader = csv.reader(csvfile, delimiter=" ", quotechar='|')
for row in reader:
# only 1 row:
y_train_sample = (list(map(int, row[0].split(','))))
pad_sequence(list(reversed([init_vector(c) for c in _ds.bw])),
_max_length_bw))
_input_fw = np.array(_input_fw)
_input_bw = np.array(_input_bw)
_length_fw = np.array(_length_fw)
_length_bw = np.array(_length_bw)
_targets = np.array(_targets)
_target_ids = np.array(_target_ids)
_nb_senses = np.array(_nb_senses)
return _input_fw, _input_bw, _length_fw, _length_bw, _targets, \
_target_ids, _nb_senses, _output_fw_idx, _output_bw_idx
if __name__ == "__main__":
TRAIN_DATA, LEMMA2SENSES, LEMMA2INT = read_data.read_train_data(
read_data.read_x("ALL.data.xml")[0],
read_data.read_y("ALL.gold.key.bnids.txt"), True)
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"""
