tf.nn.conv2d
conv2d(
input,
filter,
strides,
padding,
use_cudnn_on_gpu=True,
data_format='NHWC',
name=None
)
tf.nn.relu
relu(
features,
name=None
)
tf.nn.max_pool
max_pool(
value,
ksize,
strides,
padding,
data_format='NHWC',
name=None
)
tf.nn.dropout
dropout(
x,
keep_prob,
noise_shape=None,
seed=None,
name=None
)
tf.nn.sigmoid_cross_entropy_with_logits
功能说明:
先对 logits 通过 sigmoid 计算,再计算交叉熵
sigmoid_cross_entropy_with_logits(
_sentinel=None,
labels=None,
logits=None,
name=None
)
tf.truncated_normal
产生截断正态分布随机数,取值范围为 [ mean - 2 * stddev, mean + 2 * stddev ]。
truncated_normal(
shape,
mean=0.0,
stddev=1.0,
dtype=tf.float32,
seed=None,
name=None
)
import tensorflow as tf
initial = tf.truncated_normal(shape=[3,3], mean=0, stddev=1)
print(tf.Session().run(initial))
执行结果:
将得到一个取值范围 [ -2, 2 ] 的 3 * 3 矩阵.
tf.constant
功能说明:
根据 value 的值生成一个 shape 维度的常量张量
constant(
value,
dtype=None,
shape=None,
name='Const',
verify_shape=False
)
tf.placeholder
功能说明:
是一种占位符,在执行时候需要为其提供数据
placeholder(
dtype,
shape=None,
name=None
)