def get_final_result_multi(self):
final_result_multi = dict()
prediction_funtion = NNMultiClassModel.predict_based_on_bert_classifier
valid_2016_context_embs = self.data_embd['valid_2016']['context_embds']
valid_2016_ending_0_embs = self.data_embd['valid_2016'][
'ending0_embds']
valid_2016_ending_1_embs = self.data_embd['valid_2016'][
'ending1_embds']
valid_2016_data = self.dataset['valid_2016']
prediction_2016 = prediction_funtion(self, valid_2016_context_embs,
valid_2016_ending_0_embs,
valid_2016_ending_1_embs)
final_result_multi['valid_2016'] = compute_accuracy(
valid_2016_data, prediction_2016)
valid_2018_context_embs = self.data_embd['valid_2018']['context_embds']
valid_2018_ending_0_embs = self.data_embd['valid_2018'][
'ending0_embds']
valid_2018_ending_1_embs = self.data_embd['valid_2018'][
'ending1_embds']
valid_2018_data = self.dataset['valid_2018']
prediction_2018 = prediction_funtion(self, valid_2018_context_embs,
valid_2018_ending_0_embs,
valid_2018_ending_1_embs)
final_result_multi['valid_2018'] = compute_accuracy(
valid_2018_data, prediction_2018)
test_context_embs = self.data_embd['test']['context_embds']
test_ending_0_embs = self.data_embd['test']['ending0_embds']
test_ending_1_embs = self.data_embd['test']['ending1_embds']
test_data = self.dataset['test']
prediction_test = prediction_funtion(self, test_context_embs,
test_ending_0_embs,
test_ending_1_embs)
final_result_multi['test'] = compute_accuracy(test_data,
prediction_test)
return final_result_multi
def get_final_result_binary(self):
get_final_result_binary = dict()
prediction_funtion = NNBinaryClassModel.predict_based_on_bert_binary_classifier
test_context_embs = self.data_embd['test']['context_embds']
test_ending_0_embs = self.data_embd['test']['ending0_embds']
test_ending_1_embs = self.data_embd['test']['ending1_embds']
test_data = self.dataset['test']
prediction_test = prediction_funtion(self, test_context_embs,
test_ending_0_embs,
test_ending_1_embs)
get_final_result_binary['test'] = compute_accuracy(
test_data, prediction_test)
return get_final_result_binary
max_checkpoints_to_keep = 3
save_dir = "data/checkpoints"
train_vars = 'models/fc8-pets/weights:0,models/fc8-pets/biases:0'
# Export
export_dir = "/tmp/export/"
export_name = "pet-model" export_version = 2
images, labels = datasets.input_pipeline(dataset_dir, batch_size, is_training=True)
test_images, test_labels = datasets.input_pipeline(dataset_dir, batch_size, is_training=False)
with tf.variable_scope("models") as scope:
logits = nets.inference(images, is_training=True)
scope.reuse_variables()
test_logits = nets.inference(test_images, is_training=False)
total_loss = models.compute_loss(logits, labels)
train_accuracy = models.compute_accuracy(logits, labels)
test_accuracy = models.compute_accuracy(test_logits, test_labels)
global_step = tf.Variable(0, trainable=False)
learning_rate = models.get_learning_rate(global_step, initial_learning_rate, decay_steps, decay_rate)
train_op = models.train(total_loss, learning_rate, global_step, train_vars)
saver = tf.train.Saver(max_to_keep=max_checkpoints_to_keep)
checkpoints_dir = os.path.join(save_dir, datetime.now().strftime("%Y-%m-%d_%H-%M-%S"))
if not os.path.exists(save_dir):
os.mkdir(save_dir)
if not os.path.exists(checkpoints_dir):
os.mkdir(checkpoints_dir)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
coords = tf.train.Coordinator()
dtypes=[tf.string, tf.int64],
shapes=[(num_frames, ), ()])
train_enqueue_op = train_input_queue.enqueue_many(
[image_paths_placeholder, labels_placeholder])
frames_batch, labels_batch = input_pipeline(train_input_queue,
batch_size=batch_size,
image_size=image_size)
with tf.variable_scope("models") as scope:
logits, _ = nets.inference(frames_batch, is_training=True)
total_loss, cross_entropy_loss, reg_loss = models.compute_loss(
logits, labels_batch)
train_accuracy = models.compute_accuracy(logits, labels_batch)
global_step = tf.Variable(0, trainable=False)
learning_rate = models.get_learning_rate(global_step, initial_learning_rate,
decay_steps, decay_rate)
train_op = models.train(total_loss, learning_rate, global_step)
tf.summary.scalar("learning_rate", learning_rate)
tf.summary.scalar("train/accuracy", train_accuracy)
tf.summary.scalar("train/total_loss", total_loss)
tf.summary.scalar("train/cross_entropy_loss", cross_entropy_loss)
tf.summary.scalar("train/regularization_loss", reg_loss)
summary_op = tf.summary.merge_all()
saver = tf.train.Saver(max_to_keep=max_checkpoints_to_keep)
# step 2. compute the output
y_pred = classifier(x_in=batch_dict['x_data'].float())
# step 3. compute the loss
loss = loss_func(y_pred, batch_dict['y_target'].float())
loss_t = loss.item()
running_loss += (loss_t - running_loss) / (batch_index + 1)
# step 4. use loss to produce gradients
loss.backward()
# step 5. use optimizer to take gradient step
optimizer.step()
# -----------------------------------------
# compute the accuracy
acc_t = compute_accuracy(y_pred, batch_dict['y_target'])
running_acc += (acc_t - running_acc) / (batch_index + 1)
# update bar
# train_bar.set_postfix(loss=running_loss,
# acc=running_acc,
# epoch=epoch_index)
# train_bar.update()
train_state['train_loss'].append(running_loss)
train_state['train_acc'].append(running_acc)
# Iterate over val dataset
# setup: batch generator, set loss and acc to 0; set eval mode on
dataset.set_split('val')
logits_split, _ = nets.inference(frames_batch_split[i], is_training=True)
labels_split = labels_batch_split[i]
total_loss, cross_entropy_loss, reg_loss = models.compute_loss(logits_split, labels_split)
grads = optimizer.compute_gradients(total_loss)
total_gradients.append(grads)
tf.get_variable_scope().reuse_variables()
with tf.device('/cpu:0'):
gradients = models.average_gradients(total_gradients)
train_op = optimizer.apply_gradients(gradients, global_step)
train_accuracy = models.compute_accuracy(logits_split, labels_split)
tf.summary.scalar("learning_rate", learning_rate)
tf.summary.scalar("train/accuracy", train_accuracy)
tf.summary.scalar("train/total_loss", total_loss)
tf.summary.scalar("train/cross_entropy_loss", cross_entropy_loss)
tf.summary.scalar("train/regularization_loss", reg_loss)
summary_op = tf.summary.merge_all()
saver = tf.train.Saver(max_to_keep=max_checkpoints_to_keep)
time_stamp = datetime.now().strftime("multi_%Y-%m-%d_%H-%M-%S")
checkpoints_dir = os.path.join(save_dir, time_stamp)
summary_dir = os.path.join(checkpoints_dir, "summaries")
train_writer = tf.summary.FileWriter(summary_dir, flush_secs=10)
