本文整理汇总了Python中resnet_model.HParams方法的典型用法代码示例。如果您正苦于以下问题：Python resnet_model.HParams方法的具体用法？Python resnet_model.HParams怎么用？Python resnet_model.HParams使用的例子？那么, 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resnet_model的用法示例。
在下文中一共展示了resnet_model.HParams方法的3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 resnet_model [as 别名]
# 或者: from resnet_model import HParams [as 别名]
def main(_):
if FLAGS.num_gpus == 0:
dev = '/cpu:0'
elif FLAGS.num_gpus == 1:
dev = '/gpu:0'
else:
raise ValueError('Only support 0 or 1 gpu.')
if FLAGS.mode == 'train':
batch_size = 128
elif FLAGS.mode == 'eval':
batch_size = 100
if FLAGS.dataset == 'cifar10':
num_classes = 10
elif FLAGS.dataset == 'cifar100':
num_classes = 100
hps = resnet_model.HParams(batch_size=batch_size,
num_classes=num_classes,
min_lrn_rate=0.0001,
lrn_rate=0.1,
num_residual_units=5,
use_bottleneck=False,
weight_decay_rate=0.0002,
relu_leakiness=0.1,
optimizer='mom')
with tf.device(dev):
if FLAGS.mode == 'train':
train(hps)
elif FLAGS.mode == 'eval':
evaluate(hps) 示例2: main
# 需要导入模块: import resnet_model [as 别名]
# 或者: from resnet_model import HParams [as 别名]
def main(_):
if FLAGS.num_gpus == 0:
dev = '/cpu:0'
elif FLAGS.num_gpus == 1:
dev = '/gpu:0'
else:
raise ValueError('Only support 0 or 1 gpu.')
if FLAGS.mode == 'train':
batch_size = 128
elif FLAGS.mode == 'eval':
batch_size = 100
if FLAGS.dataset == 'cifar10':
num_classes = 10
elif FLAGS.dataset == 'cifar100':
num_classes = 100
hps = resnet_model.HParams(batch_size=batch_size,
num_classes=num_classes,
min_lrn_rate=0.0001,
lrn_rate=0.1,
num_residual_units=5,
use_bottleneck=False,
weight_decay_rate=0.0002,
relu_leakiness=0.1,
optimizer='mom')
# with tf.device(dev):
if FLAGS.mode == 'train':
train(hps)
elif FLAGS.mode == 'eval':
evaluate(hps) 示例3: eval_resnet
# 需要导入模块: import resnet_model [as 别名]
# 或者: from resnet_model import HParams [as 别名]
def eval_resnet():
"""Evaluates the resnet model."""
if not os.path.exists(FLAGS.eval_dir):
os.makedirs(FLAGS.eval_dir)
g = tf.Graph()
with g.as_default():
# pylint: disable=line-too-long
images, one_hot_labels, num_samples, num_of_classes = cifar_data_provider.provide_resnet_data(
FLAGS.dataset_name,
FLAGS.split_name,
FLAGS.batch_size,
dataset_dir=FLAGS.data_dir,
num_epochs=None)
hps = resnet_model.HParams(
batch_size=FLAGS.batch_size,
num_classes=num_of_classes,
min_lrn_rate=0.0001,
lrn_rate=0,
num_residual_units=9,
use_bottleneck=False,
weight_decay_rate=0.0002,
relu_leakiness=0.1,
optimizer='mom')
# Define the model:
images.set_shape([FLAGS.batch_size, 32, 32, 3])
resnet = resnet_model.ResNet(hps, images, one_hot_labels, mode='test')
logits = resnet.build_model()
total_loss = tf.nn.softmax_cross_entropy_with_logits(
labels=one_hot_labels, logits=logits)
total_loss = tf.reduce_mean(total_loss, name='xent')
slim.summaries.add_scalar_summary(
total_loss, 'total_loss', print_summary=True)
# Define the metrics:
predictions = tf.argmax(logits, 1)
labels = tf.argmax(one_hot_labels, 1)
names_to_values, names_to_updates = slim.metrics.aggregate_metric_map({
'accuracy': tf.metrics.accuracy(predictions, labels),
})
for name, value in names_to_values.iteritems():
slim.summaries.add_scalar_summary(
value, name, prefix='eval', print_summary=True)
# This ensures that we make a single pass over all of the data.
num_batches = math.ceil(num_samples / float(FLAGS.batch_size))
slim.evaluation.evaluation_loop(
master=FLAGS.master,
checkpoint_dir=FLAGS.checkpoint_dir,
logdir=FLAGS.eval_dir,
num_evals=num_batches,
eval_op=names_to_updates.values(),
eval_interval_secs=FLAGS.eval_interval_secs)