本文整理汇总了Python中tfcode.tf_utils.distort_image方法的典型用法代码示例。如果您正苦于以下问题：Python tf_utils.distort_image方法的具体用法？Python tf_utils.distort_image怎么用？Python tf_utils.distort_image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tfcode.tf_utils的用法示例。
在下文中一共展示了tf_utils.distort_image方法的1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: get_repr_from_image
# 需要导入模块: from tfcode import tf_utils [as 别名]
# 或者: from tfcode.tf_utils import distort_image [as 别名]
def get_repr_from_image(images_reshaped, modalities, data_augment, encoder,
freeze_conv, wt_decay, is_training):
# Pass image through lots of convolutional layers, to obtain pool5
if modalities == ['rgb']:
with tf.name_scope('pre_rgb'):
x = (images_reshaped + 128.) / 255. # Convert to brightness between 0 and 1.
if data_augment.relight and is_training:
x = tf_utils.distort_image(x, fast_mode=data_augment.relight_fast)
x = (x-0.5)*2.0
scope_name = encoder
elif modalities == ['depth']:
with tf.name_scope('pre_d'):
d_image = images_reshaped
x = 2*(d_image[...,0] - 80.0)/100.0
y = d_image[...,1]
d_image = tf.concat([tf.expand_dims(x, -1), tf.expand_dims(y, -1)], 3)
x = d_image
scope_name = 'd_'+encoder
resnet_is_training = is_training and (not freeze_conv)
with slim.arg_scope(resnet_v2.resnet_utils.resnet_arg_scope(resnet_is_training)):
fn = getattr(tf_utils, encoder)
x, end_points = fn(x, num_classes=None, global_pool=False,
output_stride=None, reuse=None,
scope=scope_name)
vars_ = slim.get_variables_to_restore()
conv_feat = x
return conv_feat, vars_