吴裕雄--天生自然深度学习TensorBoard可视化:projector_MNIST
摘要:import os import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data from tensorflow.contrib.tensorboard.plugins import projector INPUT_NODE = 784 OUTPUT_NODE = 10 LAYER1_NODE
阅读全文
吴裕雄--天生自然深度学习TensorBoard可视化:projector_data_prepare
摘要:import os import numpy as np import tensorflow as tf import matplotlib.pyplot as plt from tensorflow.examples.tutorials.mnist import input_data %matplotlib inline LOG_DIR = 'F:\\temp\\log\\' SPRITE_FI
阅读全文
吴裕雄--天生自然深度学习TensorBoard可视化:监控指标可视化
摘要:import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data # 1. 生成变量监控信息并定义生成监控信息日志的操作。 SUMMARY_DIR = "F:\\temp\\log" BATCH_SIZE = 100 TRAIN_STEPS = 3000 def variable_summaries
阅读全文
吴裕雄--天生自然深度学习TensorBoard可视化:改造后的mnist_train
摘要:import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data INPUT_NODE = 784 OUTPUT_NODE = 10 LAYER1_NODE = 500 def get_weight_variable(shape, regularizer): weights = tf.get_var
阅读全文
吴裕雄--天生自然深度学习TensorBoard可视化:命名空间
摘要:# 1. 不同的命名空间。 import tensorflow as tf with tf.variable_scope("foo"): a = tf.get_variable("bar", [1]) print(a.name) with tf.variable_scope("bar"): b = tf.get_variable("bar", [1]) pri...
阅读全文