def train():
def getTrainBatch():
labels = []
arr = np.zeros([BATCH_SIZE, MAX_WORDS_IN_REVIEW, EMBEDDING_SIZE])
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_embedded[num, :, :]
return arr, labels
tf.reset_default_graph()
# Call implementation
glove_array, glove_dict = load_glove_embeddings()
training_data_text = load_data()
training_data_embedded = embedd_data(training_data_text, glove_array, glove_dict)
input_data, labels, dropout_keep_prob, optimizer, accuracy, loss = \
imp.define_graph()
# tensorboard
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(
"%Y%m%d-%H%M%S") + "/"
writer = tf.summary.FileWriter(logdir, sess.graph)
for i in range(iterations):
batch_data, batch_labels = getTrainBatch()
sess.run(optimizer, {input_data: batch_data, labels: batch_labels,
dropout_keep_prob: 0.6})
if (i % 50 == 0):
loss_value, accuracy_value, summary = sess.run(
[loss, accuracy, summary_op],
{input_data: batch_data,
labels: batch_labels})
writer.add_summary(summary, i)
print("Iteration: ", i)
print("loss", loss_value)
print("acc", accuracy_value)
if (i % SAVE_FREQ == 0 and i != 0):
if not os.path.exists(checkpoints_dir):
os.makedirs(checkpoints_dir)
save_path = all_saver.save(sess, checkpoints_dir +
"/trained_model.ckpt",
global_step=i)
print("Saved model to %s" % save_path)
sess.close()
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()
sess.run(tf.global_variables_initializer())
str_time = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
train_logdir = "tensorboard/" + str_time + "-train/"
test_logdir = "tensorboard/" + str_time + "-test/"
arr = np.zeros([batch_size, 40])
for i in range(batch_size):
num = randint(10000, 14499)
if (num <= 12499):
labels.append([1, 0])
else:
labels.append([0, 1])
arr[i] = training_data[num - 1: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(
"%Y%m%d-%H%M%S") + "/"
writer = tf.summary.FileWriter(logdir, sess.graph)
def train():
def getTrainBatch():
labels = []
arr = np.zeros([BATCH_SIZE, MAX_WORDS_IN_REVIEW, EMBEDDING_SIZE])
for i in range(BATCH_SIZE):
if (i % 5 == 0):
num = randint(0, 35999)
labels.append([1, 0, 0, 0, 0])
elif (i % 5 == 1):
num = randint(36000, 71999)
labels.append([0, 1, 0, 0, 0])
elif (i % 5 == 2):
num = randint(72000, 107999)
labels.append([0, 0, 1, 0, 0])
elif (i % 5 == 3):
num = randint(108000, 143999)
labels.append([0, 0, 0, 1, 0])
elif (i % 5 == 4):
num = randint(144000, 179999)
labels.append([0, 0, 0, 0, 1])
arr[i] = training_data_embedded[num, :, :]
return arr, labels
# Call implementation
glove_array, glove_dict = load_glove_embeddings()
training_data_text = load_data()
# pprint(training_data_text)
# ========= FOR EVAL =========
data_text = load_data(path=dir_path + "/data/validate")
test_data = embedd_data(data_text, glove_array, glove_dict)
num_samples = len(test_data)
# ========= FOR EVAL =========
training_data_embedded = embedd_data(training_data_text, glove_array,
glove_dict)
input_data, labels, dropout_keep_prob, optimizer, accuracy, loss = \
imp.define_graph()
# tensorboard
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())
for i in range(iterations):
batch_data, batch_labels = getTrainBatch()
sess.run(optimizer, {
input_data: batch_data,
labels: batch_labels,
dropout_keep_prob: 0.6
})
if (i % 50 == 0):
loss_value, accuracy_value, summary = sess.run(
[loss, accuracy, summary_op], {
input_data: batch_data,
labels: batch_labels
})
print("Iteration: ", i)
print("loss", loss_value)
print("acc", accuracy_value)
if (i % SAVE_FREQ == 0 and i != 0):
if not os.path.exists(checkpoints_dir):
os.makedirs(checkpoints_dir)
save_path = all_saver.save(sess,
checkpoints_dir + "/trained_model.ckpt",
global_step=i)
print("Saved model to %s" % save_path)
print("Running eval now")
num_batches = num_samples // BATCH_SIZE
label_list = [[1, 0, 0, 0, 0]] * (num_samples // 5)
label_list.extend([[0, 1, 0, 0, 0]] * (num_samples // 5))
label_list.extend([[0, 0, 1, 0, 0]] * (num_samples // 5))
label_list.extend([[0, 0, 0, 1, 0]] * (num_samples // 5))
label_list.extend([[0, 0, 0, 0, 1]] * (num_samples // 5))
assert (len(label_list) == num_samples)
total_acc = 0
for i in range(num_batches):
sample_index = i * BATCH_SIZE
batch = test_data[sample_index:sample_index + BATCH_SIZE]
batch_labels = label_list[sample_index:sample_index +
BATCH_SIZE]
lossV, accuracyV = sess.run([loss, accuracy], {
input_data: batch,
labels: batch_labels
})
total_acc += accuracyV
print("Accuracy %s, Loss: %s" % (accuracyV, lossV))
print('-' * 40)
print("FINAL ACC:", total_acc / num_batches)
#new_sess.close()
sess.close()
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(
"%Y%m%d-%H%M%S") + "/"
writer = tf.summary.FileWriter(logdir, sess.graph)
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(
"%Y%m%d-%H%M%S") + "/"
writer = tf.summary.FileWriter(logdir, sess.graph)
# Call implementation
# glove_array, glove_dict = imp.load_glove_embeddings()
# training_data = imp.load_data(glove_dict)
# np.save('glove_array', glove_array)
# np.save('glove_dict', glove_dict)
# np.save('training_data',training_data)
glove_array = np.load('glove_array.npy')
glove_dict = np.load('glove_dict.npy').item()
training_data = np.load('training_data.npy')
Xtrain, Ytrain, Xtest, Ytest = imp.split_data(training_data, train_test_split)
input_data, labels, dropout_keep_prob, optimizer, accuracy, loss = \
imp.define_graph(glove_array, batch_size)
# 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(
"%Y%m%d-%H%M%S") + "/"
writer = tf.summary.FileWriter(logdir, sess.graph)
def train():
def getTrainBatch():
labels = []
arr = np.zeros([BATCH_SIZE, MAX_WORDS_IN_REVIEW, EMBEDDING_SIZE])
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_embedded[num, :, :]
return arr, labels
# Call implementation
glove_array, glove_dict = load_glove_embeddings()
training_data_text = load_zip(dataset='train')
training_data_embedded = embedd_data(training_data_text, glove_array,
glove_dict)
input_data, labels, dropout_keep_prob, optimizer, accuracy, loss, training = \
imp.define_graph()
# call the validation data
glove_array, glove_dict = load_glove_embeddings()
data_text = load_zip(dataset='validate')
test_data = embedd_data(data_text, glove_array, glove_dict)
num_samples = len(test_data)
num_batches = num_samples // BATCH_SIZE
label_list = [[1, 0]] * (num_samples // 2
) # pos always first, neg always second
label_list.extend([[0, 1]] * (num_samples // 2))
assert (len(label_list) == num_samples)
# tensorboard
accuracy_validation = tf.placeholder_with_default(
0.0, shape=(), name="accuracy_validation")
loss_validation = tf.placeholder_with_default(0.0,
shape=(),
name="loss_validation")
tf.summary.scalar("dev_acc", accuracy_validation)
tf.summary.scalar("dev_loss", loss_validation)
summary_op = tf.summary.merge_all()
# saver
all_saver = tf.train.Saver()
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())
logdir_train = "tensorboard/" + datetime.datetime.now().strftime(
"%Y%m%d-%H%M%S-train") + "/"
logdir_test = "tensorboard/" + datetime.datetime.now().strftime(
"%Y%m%d-%H%M%S-test") + "/"
writer_train = tf.summary.FileWriter(logdir_train, sess.graph)
writer_test = tf.summary.FileWriter(logdir_test, sess.graph)
for i in range(iterations):
batch_data, batch_labels = getTrainBatch()
sess.run(
optimizer, {
input_data: batch_data,
labels: batch_labels,
dropout_keep_prob: 0.6,
training: True
})
if (i % 50 == 0):
loss_value, accuracy_value = sess.run([loss, accuracy], {
input_data: batch_data,
labels: batch_labels
})
_, _, sum_train = sess.run(
[loss_validation, accuracy_validation, summary_op], {
loss_validation: loss_value,
accuracy_validation: accuracy_value
})
writer_train.add_summary(sum_train, i)
print("INFO-Iteration: ", i, end=' - ')
print("loss: ", loss_value, end=' - ')
print("accuracy: ", accuracy_value)
if (i % SAVE_FREQ == 0 and i != 0):
if not os.path.exists(checkpoints_dir):
os.makedirs(checkpoints_dir)
save_path = all_saver.save(sess,
checkpoints_dir + "/trained_model.ckpt",
global_step=i)
print("Saved model to %s" % save_path)
if i % validatefreq == 0 and i != 0:
print(
"------------------validation mode activated---------------------"
)
total_acc = 0
total_lost = 0
for j in range(num_batches):
sample_index = j * BATCH_SIZE
batch_dev = test_data[sample_index:sample_index + BATCH_SIZE]
batch_labels_dev = label_list[sample_index:sample_index +
BATCH_SIZE]
lossV, accuracyV = sess.run([loss, accuracy], {
input_data: batch_dev,
labels: batch_labels_dev
})
total_acc += accuracyV
total_lost += lossV
_, _, validation = sess.run(
[accuracy_validation, loss_validation, summary_op],
feed_dict={
accuracy_validation: total_acc / num_batches,
loss_validation: total_lost / num_batches
})
writer_test.add_summary(validation, i)
print("Validation INFO-", end='')
print("average accuracy: ", total_acc / num_batches, end=' - ')
print("average loss: ", total_lost / num_batches)
print(
"------------------------------end-------------------------------"
)
sess.close()
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, 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(
"%Y%m%d-%H%M%S") + "/"
writer = tf.summary.FileWriter(logdir, sess.graph)
