PointNet在实际搭建网络结构时,其实是将 N×3 N × 3 的点云当作图片处理,即height=N
,width=3
。作者对其搭建网络所用到的各种层进行了二次封装,存放于tf_util.py中。本文主要对常用到的conv2D,fc,max_pool源码进行分析。
def _variable_with_weight_decay(name, shape, stddev, wd, use_xavier=True):
"""Helper to create an initialized Variable with weight decay.
Note that the Variable is initialized with a truncated normal distribution.
A weight decay is added only if one is specified.
Args:
name: name of the variable
shape: list of ints
stddev: standard deviation of a truncated Gaussian
wd: add L2Loss weight decay multiplied by this float. If None, weight
decay is not added for this Variable.
use_xavier: bool, whether to use xavier initializer
Returns:
Variable Tensor
"""
if use_xavier:
initializer = tf.contrib.layers.xavier_initializer()
else:
initializer = tf.truncated_normal_initializer(stddev=stddev)
var = _variable_on_cpu(name, shape, initializer)
if wd is not None:
weight_decay = tf.multiply(tf.nn.l2_loss(var), wd, name='weight_loss')
tf.add_to_collection('losses', weight_decay)
return var
用于初始化参数
def conv2d(inputs,
num_output_channels,
kernel_size,
scope,
stride=[1, 1],
padding='SAME',
use_xavier=True,
stddev=1e-3,
weight_decay=0.0,
activation_fn=tf.nn.relu,
bn=False,
bn_decay=None,
is_training=None):
""" 2D convolution with non-linear operation.
Args:
inputs: 4-D tensor variable BxHxWxC
num_output_channels: int
kernel_size: a list of 2 ints
scope: string
stride: a list of 2 ints
padding: 'SAME' or 'VALID'
use_xavier: bool, use xavier_initializer if true
stddev: float, stddev for truncated_normal init
weight_decay: float
activation_fn: function
bn: bool, whether to use batch norm
bn_decay: float or float tensor variable in [0,1]
is_training: bool Tensor variable
Returns:
Variable tensor
"""
with tf.variable_scope(scope) as sc:
kernel_h, kernel_w = kernel_size
num_in_channels = inputs.get_shape()[-1].value
kernel_shape = [kernel_h, kernel_w,
num_in_channels, num_output_channels]
kernel = _variable_with_weight_decay('weights',
shape=kernel_shape,
use_xavier=use_xavier,
stddev=stddev,
wd=weight_decay)
stride_h, stride_w = stride
outputs = tf.nn.conv2d(inputs, kernel,
[1, stride_h, stride_w, 1],
padding=padding)
biases = _variable_on_cpu('biases', [num_outp