最近做实验在用,这里存一些: Tensorflow和Pytorch函数转换对照表 TENSORFLOW与PYTORCH:区别及函数习惯的对比 如侵必删
tensorflow的一个神经网络层:
def add_layer(input,in_size,out_size,activation_function=None):
"""
:param input: 数据输入
:param in_size: 输入大小
:param out_size: 输出大小
:param activation_function: 激活函数(默认没有)
:return:output:数据输出
"""
Weight=tf.Variable(tf.random_normal([in_size,out_size]) )
biases=tf.Variable(tf.zeros([1,out_size]) +0.1 )
W_mul_x_plus_b=tf.matmul(input,Weight) + biases
if activation_function == None:
output=W_mul_x_plus_b
else:
output=activation_function(W_mul_x_plus_b)
return output
batch_norm 层:
def batch_norm(x):
epsilon = 1e-5
batch_mean, batch_var = tf.nn.moments(x, [0])
return tf.nn.batch_normalization(x, batch_mean, batch_var,
offset=None, scale=None,
variance_epsilon=epsilon)
|