for i in range(batch_size):
if (i % 2 == 0):
num = randint(0, 12499)
labels.append([1, 0])
else:
num = randint(12500, 24999)
labels.append([0, 1])
arr[i] = test_data[num]
return arr, labels
# Call implementation
glove_array, glove_dict = imp.load_glove_embeddings()
print("Loaded glove")
training_data = imp.load_data(glove_dict)
test_data = imp.load_data(glove_dict, test=True)
print("Loaded data")
input_data, labels, dropout_keep_prob, optimizer, accuracy, loss = \
imp.define_graph(glove_array)
# tensorboard
train_acc_op = tf.summary.scalar("training_accuracy", accuracy)
test_acc_op = tf.summary.scalar("testing_accuracy", accuracy)
#tf.summary.scalar("loss", loss)
#summary_op = tf.summary.merge_all()
# saver
all_saver = tf.train.Saver()
def getTestBatch2(training_data):
labels = []
arr = np.zeros([batch_size, seq_length])
for i in range(batch_size):
num = randint(11499, 13499)
if (num <= 12499):
labels.append([1, 0])
else:
labels.append([0, 1])
arr[i] = training_data[num]
return arr, labels
# Call implementation
glove_array, glove_dict = imp.load_glove_embeddings()
training_data = imp.load_data(glove_dict)
print('Size of training data: ', len(training_data))
input_data, labels, dropout_keep_prob, optimizer, accuracy, loss = imp.define_graph(
glove_array)
# tensorboard
train_accuracy_op = tf.summary.scalar("accuracy", accuracy)
tf.summary.scalar("loss", loss)
summary_op = tf.summary.merge_all()
# saver
all_saver = tf.train.Saver()
sess = tf.InteractiveSession()
def getTrainBatch():
labels = []
arr = np.zeros([batch_size, seq_length])
for i in range(batch_size):
if (i % 2 == 0):
num = randint(0, 12499)
labels.append([1, 0])
else:
num = randint(12500, 24999)
labels.append([0, 1])
arr[i] = training_data[num]
return arr, labels
# Call implementation
glove_array, glove_dict = imp.load_glove_embeddings()
training_data = imp.load_data(glove_dict)
input_data, labels, dropout_keep_prob, optimizer, accuracy, loss = \
imp.define_graph(glove_array)
# tensorboard
train_accuracy_op = tf.summary.scalar("training_accuracy", accuracy)
tf.summary.scalar("loss", loss)
summary_op = tf.summary.merge_all()
# saver
all_saver = tf.train.Saver()
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())
logdir = "tensorboard/" + datetime.datetime.now().strftime(
def getTrainBatch():
labels = []
arr = np.zeros([batch_size, seq_length])
for i in range(batch_size):
num = randint(0, training_data.shape[0] - 1)
label = [0, 0, 0, 0]
label[training_classes[num]] = 1
labels.append(label)
arr[i] = training_data[num]
return arr, labels
# Call implementation
word2vec_array, word2vec_dict = imp.load_word2vec_embeddings()
training_data, training_classes = imp.load_data(word2vec_dict)
input_data, labels, dropout_keep_prob, optimizer, accuracy, loss = \
imp.define_graph(word2vec_array)
# tensorboard
train_accuracy_op = tf.summary.scalar("training_accuracy", accuracy)
tf.summary.scalar("loss", loss)
summary_op = tf.summary.merge_all()
# saver
all_saver = tf.train.Saver()
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())
logdir = "tensorboard/" + datetime.datetime.now().strftime(
checkpoints_dir = "./checkpoints"
def getTrainBatch(data, labels):
sample = np.random.randint(data.shape[0], size=batch_size)
arr = data[sample, :]
lab = labels[sample, :]
return arr, lab
# Call implementation
glove_array, glove_dict = imp.load_glove_embeddings()
print("Loaded glove")
training_data, training_labels = imp.load_data(glove_dict)
print("Loaded data")
input_data, labels, dropout_keep_prob, optimizer, accuracy, loss = \
imp.define_graph(glove_array)
# tensorboard
train_acc_op = tf.summary.scalar("training_accuracy", accuracy)
#tf.summary.scalar("loss", loss)
#summary_op = tf.summary.merge_all()
# saver
all_saver = tf.train.Saver()
arr = np.zeros([batch_size, seq_length])
for i in range(batch_size):
num = offset + i
label = [0] * num_classes
label[validation_classes[num]] = 1
labels.append(label)
arr[i] = validation_data[num]
fnames.append(validation_fnames[num])
return arr, labels, fnames
# Call implementation
word2vec_array, word2vec_dict = gensim_load.load_google_embeddings(
) # imp.load_word2vec_embeddings()
# word2vec_array, word2vec_dict = imp.load_word2vec_embeddings()
training_data, training_classes, training_fnames, training_o_comps = imp.load_data(
word2vec_dict)
original_data = training_data[:, :]
original_classes = training_classes[:]
original_fnames = training_fnames[:]
original_o_comps = training_o_comps[:]
training_data, training_classes, training_fnames, training_o_comps, \
validation_data, validation_classes, validation_fnames, validation_o_comps = \
validation_split(0.2)
gensim_load.log(",".join(training_fnames))
input_data, labels, dropout_keep_prob, optimizer, accuracy, loss, \
prediction, correct_pred, pred_class, pred_prob = \
imp.define_graph(word2vec_array)
# tensorboard
"""This module runs tests"""
from implementation import load_glove_embeddings, load_data, define_graph
import os
import numpy as np
import tensorflow as tf
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
embeddings, word_index_dict = load_glove_embeddings()
data = load_data(word_index_dict, test=True)
def getValBatch():
labels = []
arr = np.zeros([25000, 40])
for i in range(25000):
if i < 12500:
arr[i] = data[i]
labels.append([1, 0])
else:
arr[i] = data[i]
labels.append([0, 1])
return arr, labels
val_data, val_labels = getValBatch()
saver = tf.train.import_meta_graph(
'./checkpoints/trained_model.ckpt-50000.meta')