本文整理汇总了Python中model_rotator.preprocess方法的典型用法代码示例。如果您正苦于以下问题:Python model_rotator.preprocess方法的具体用法?Python model_rotator.preprocess怎么用?Python model_rotator.preprocess使用的例子?那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类model_rotator
的用法示例。
在下文中一共展示了model_rotator.preprocess方法的2个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: main
# 需要导入模块: import model_rotator [as 别名]
# 或者: from model_rotator import preprocess [as 别名]
def main(argv=()):
del argv # Unused.
eval_dir = os.path.join(FLAGS.checkpoint_dir,
FLAGS.model_name, 'train')
log_dir = os.path.join(FLAGS.checkpoint_dir,
FLAGS.model_name, 'eval')
if not os.path.exists(eval_dir):
os.makedirs(eval_dir)
if not os.path.exists(log_dir):
os.makedirs(log_dir)
g = tf.Graph()
if FLAGS.step_size < FLAGS.num_views:
raise ValueError('Impossible step_size, must not be less than num_views.')
g = tf.Graph()
with g.as_default():
##########
## data ##
##########
val_data = model.get_inputs(
FLAGS.inp_dir,
FLAGS.dataset_name,
'val',
FLAGS.batch_size,
FLAGS.image_size,
is_training=False)
inputs = model.preprocess(val_data, FLAGS.step_size)
###########
## model ##
###########
model_fn = model.get_model_fn(FLAGS, is_training=False)
outputs = model_fn(inputs)
#############
## metrics ##
#############
names_to_values, names_to_updates = model.get_metrics(
inputs, outputs, FLAGS)
del names_to_values
################
## evaluation ##
################
num_batches = int(val_data['num_samples'] / FLAGS.batch_size)
slim.evaluation.evaluation_loop(
master=FLAGS.master,
checkpoint_dir=eval_dir,
logdir=log_dir,
num_evals=num_batches,
eval_op=names_to_updates.values(),
eval_interval_secs=FLAGS.eval_interval_secs)
示例2: main
# 需要导入模块: import model_rotator [as 别名]
# 或者: from model_rotator import preprocess [as 别名]
def main(argv=()):
del argv # Unused.
eval_dir = os.path.join(FLAGS.checkpoint_dir,
FLAGS.model_name, 'train')
log_dir = os.path.join(FLAGS.checkpoint_dir,
FLAGS.model_name, 'eval')
if not os.path.exists(eval_dir):
os.makedirs(eval_dir)
if not os.path.exists(log_dir):
os.makedirs(log_dir)
g = tf.Graph()
if FLAGS.step_size < FLAGS.num_views:
raise ValueError('Impossible step_size, must not be less than num_views.')
g = tf.Graph()
with g.as_default():
##########
## data ##
##########
val_data = model.get_inputs(
FLAGS.data_sst_path,
FLAGS.dataset_name,
'val',
FLAGS.batch_size,
FLAGS.image_size,
is_training=False)
inputs = model.preprocess(val_data, FLAGS.step_size)
###########
## model ##
###########
model_fn = model.get_model_fn(FLAGS, is_training=False)
outputs = model_fn(inputs)
#############
## metrics ##
#############
names_to_values, names_to_updates = model.get_metrics(
inputs, outputs, FLAGS)
del names_to_values
################
## evaluation ##
################
num_batches = int(val_data['num_samples'] / FLAGS.batch_size)
slim.evaluation.evaluation_loop(
master=FLAGS.master,
checkpoint_dir=eval_dir,
logdir=log_dir,
num_evals=num_batches,
eval_op=names_to_updates.values(),
eval_interval_secs=FLAGS.eval_interval_secs)