def __init__(self):
# Load the parameters
args = EvaluatePointConfig()
json_path = os.path.join(args.model_dir, 'params.json')
assert os.path.isfile(
json_path), "No json configuration file found at {}".format(
json_path)
params = Params(json_path)
if params.mlp_sizes is None or len(params.mlp_sizes) == 0:
logging.error(
'mlp_sizes are not set correctly, at least one MLP layer is required'
)
params.dict['loss_fn'] = args.loss_fn
# Load the parameters from the dataset, that gives the size etc. into params
json_path = os.path.join(args.data_dir, 'dataset_params.json')
assert os.path.isfile(
json_path), "No json file found at {}, run build.py".format(
json_path)
params.update(json_path)
# Set the logger
set_logger(os.path.join(args.model_dir, 'evaluate.log'))
# # Get paths for tfrecords
path_eval_tfrecords = os.path.join(args.data_dir,
'test_' + args.tfrecords_filename)
# Create the input data pipeline
logging.info("Creating the dataset...")
eval_dataset = load_dataset_from_tfrecords(path_eval_tfrecords)
# Create iterator over the test set
# eval_inputs = input_fn('test', eval_dataset, params)
eval_inputs = online_input_fn()
logging.info("- done.")
# print(type(eval_inputs))
# Define the model
logging.info("Creating the model...")
weak_learner_id = load_best_ndcgs(
os.path.join(args.model_dir, args.restore_from, 'learner.json'))[0]
self.model_spec = model_fn('test',
eval_inputs,
params,
reuse=False,
weak_learner_id=int(weak_learner_id))
# node_names = [n.name for n in tf.get_default_graph().as_graph_def().node]
# print(node_names)
logging.info("- done.")
logging.info("Starting evaluation")
logging.info("Optimized using {} learners".format(weak_learner_id))
self.saver = tf.train.Saver()
self.sess = tf.Session()
self.params = params
self.sess.run(self.model_spec['variable_init_op'])
save_path = os.path.join(args.model_dir, args.restore_from)
if os.path.isdir(save_path):
save_path = tf.train.latest_checkpoint(save_path)
self.saver.restore(self.sess, save_path)
path_train_tfrecords = os.path.join(args.data_dir,
'train_' + args.tfrecords_filename)
path_eval_tfrecords = os.path.join(args.data_dir,
'eval_' + args.tfrecords_filename)
# Create the input data pipeline
logging.info("Creating the datasets...")
train_dataset = load_dataset_from_tfrecords(path_train_tfrecords)
eval_dataset = load_dataset_from_tfrecords(path_eval_tfrecords)
# Specify other parameters for the dataset and the model
# Create the two iterators over the two datasets
train_inputs = input_fn('train', train_dataset, params)
eval_inputs = input_fn('vali', eval_dataset, params)
logging.info("- done.")
# Define the models (2 different set of nodes that share weights for train and validation)
logging.info("Creating the model...")
train_model_spec = model_fn('train', train_inputs, params)
eval_model_spec = model_fn('vali', eval_inputs, params, reuse=True)
logging.info("- done.")
# Train the model
# log tim
# start_time = time.time()
logging.info("Starting training for {} epoch(s)".format(params.num_epochs))
train_and_evaluate(train_model_spec, eval_model_spec, args.model_dir,
params, args.restore_dir)
# print("--- %s seconds ---" % (time.time() - start_time))
params = Params(json_path)
params.dict['loss_fn'] = args.loss_fn
params.dict['collect'] = False
params.dict['use_kfac'] = args.use_kfac
params.dict['finetune'] = args.finetune
params.dict['training_keep_prob'] = 1.0
# Load the parameters from the dataset, that gives the size etc. into params
json_path = os.path.join(args.data_dir, 'dataset_params.json')
assert os.path.isfile(json_path), "No json file found at {}, run build.py".format(json_path)
params.update(json_path)
# Set the logger
set_logger(os.path.join(args.model_dir, 'test{}.log'.format(args.log)))
# # Get paths for tfrecords
dataset = 'test'
path_eval_tfrecords = os.path.join(args.data_dir, dataset + args.tfrecords_filename)
# Create the input data pipeline
logging.info("Creating the dataset...")
eval_dataset = load_dataset_from_tfrecords(path_eval_tfrecords)
# Create iterator over the test set
eval_inputs = input_fn('test', eval_dataset, params)
logging.info("- done.")
# Define the model
logging.info("Creating the model...")
# weak_learner_id = load_learner_id(os.path.join(args.model_dir, args.restore_from, 'learner.json'))[0]
eval_model_spec = model_fn('test', eval_inputs, params, reuse=False)
# node_names = [n.name for n in tf.get_default_graph().as_graph_def().node]
# print(node_names)
logging.info("- done.")
logging.info("Starting evaluation")
evaluate(eval_model_spec, args.model_dir, params, args.restore_from)
path_eval_tfrecords = os.path.join(
args.data_dir, 'validation' + args.tfrecords_filename)
print(path_train_tfrecords)
# Create the input data pipeline
logging.info("Creating the datasets...")
train_dataset = load_dataset_from_tfrecords(
glob.glob(path_train_tfrecords))
eval_dataset = load_dataset_from_tfrecords(path_eval_tfrecords)
# Specify other parameters for the dataset and the model
# Create the two iterators over the two datasets
train_inputs = input_fn('train', train_dataset, params)
eval_inputs = input_fn('vali', eval_dataset, params)
logging.info("- done.")
# Define the models (2 different set of nodes that share weights for train and validation)
logging.info("Creating the model...")
train_model_spec = model_fn('train', train_inputs, params)
eval_model_spec = model_fn('vali', eval_inputs, params, reuse=True)
logging.info("- done.")
logging.info(
"Starting training for at most {} epoch(s) for the initial learner"
.format(params.num_epochs))
start_time = time.time()
global_epoch = train_and_evaluate(train_model_spec, eval_model_spec, args.model_dir, params, \
learner_id=0, restore_from=args.restore_dir)
logging.info(
"global_epoch: {} epoch(s) at learner 0".format(global_epoch))
logging.info("total time: %s seconds ---" % (time.time() - start_time))
# start gradient boosting
last_global_epoch = global_epoch
if (params.num_learners > 1):
args.train_range)
# print(params.dict)
global_epoch = 0
args.restore_dir = 'best_weights'
path_train_tfrecords = os.path.join(
args.data_dir,
'train-{}'.format(args.train_range) + args.tfrecords_filename)
# Create the input data pipeline
logging.info("Creating the datasets...")
train_dataset = load_dataset_from_tfrecords(
glob.glob(path_train_tfrecords))
#########################################################
params.dict['training_keep_prob'] = 1.0
start_time = time.time()
train_dataset = load_dataset_from_tfrecords(
glob.glob(path_train_tfrecords))
# Specify other parameters for the dataset and the model
# Create the two iterators over the two datasets
train_inputs = input_fn('vali', train_dataset, params)
evaluate_on_train_model_spec = model_fn('vali',
train_inputs,
params,
reuse=True)
logging.info("- done.")
args.restore_dir = 'best_weights'
global_epoch = evaluate_on_train(evaluate_on_train_model_spec,
args.model_dir, params, restore_from=args.restore_dir,\
global_epoch=global_epoch)
logging.info("global_epoch: {} epoch(s)".format(global_epoch))
logging.info("total time: %s seconds ---" % (time.time() - start_time))
params.dict['test_size'] = params.dict['test_size'] * 2
print('USING both Tests')
# logging.info("test size: {}".format(params.test_size))
dataset += '*'
path_eval_tfrecords = os.path.join(args.data_dir, dataset + args.tfrecords_filename)
# Create the input data pipeline
logging.info("Creating the dataset...")
eval_dataset = load_dataset_from_tfrecords(glob.glob(path_eval_tfrecords))
else:
if args.aug:
print('USING augmented TEST')
dataset += '_aug'
path_eval_tfrecords = os.path.join(args.data_dir, dataset + args.tfrecords_filename)
# Create the input data pipeline
logging.info("Creating the dataset...")
eval_dataset = load_dataset_from_tfrecords(path_eval_tfrecords)
# Create iterator over the test set
eval_inputs = input_fn('test', eval_dataset, params)
logging.info("- done.")
# Define the model
logging.info("Creating the model...")
weak_learner_id = load_learner_id(os.path.join(args.model_dir, args.restore_from, 'learner.json'))[0]
eval_model_spec = model_fn('test', eval_inputs, params, reuse=False, \
weak_learner_id=int(weak_learner_id))
# node_names = [n.name for n in tf.get_default_graph().as_graph_def().node]
# print(node_names)
logging.info("- done.")
logging.info("Starting evaluation")
logging.info("Optimized using {} learners".format(weak_learner_id))
evaluate(eval_model_spec, args.model_dir, params, args.restore_from)