Jolen_xie的博客

https://www.cnblogs.com/zyly/p/9146787.html

清华源镜像下载地址https://pypi.tuna.tsinghua.edu.cn/simple/tensorflow-gpu/

with tf.Graph().as_default(): ....model().... update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS) with tf.control_dependencies(update_ops): optimizer = tf.train.AdamOptimizer(learning_rate).minimize(loss, global_step=global_step) var_list = tf

先引入头文件import tensorflow as tf1.计算参数量def count_param(): # 计算网络参数量 total_parameters = 0 for v in tf.trainable_variables(): shape = v.get_shape() variable_parameters = 1 for dim in shape: variable_paramete