摘要: 0. Review 1. Computation graph TensorFlow separates definition of computations from their execution Phase 1: assemble a graph Phase 2: use a session t 阅读全文
posted @ 2019-02-12 17:50 hzhang_NJU 阅读(289) 评论(0) 推荐(0) 编辑
摘要: 1. Tensorboard 1. tensorboard使用 Note : If you've run your code several times, there will be multiple event files in your [logdir]. TF will show only t 阅读全文
posted @ 2019-02-12 17:47 hzhang_NJU 阅读(177) 评论(0) 推荐(0) 编辑
摘要: 1. Agenda Basic operations Tensor types Importing data Lazy loading 2. Basic operations 1. tensorborad使用介绍 2. Constants, Sequences, Variables, Ops con 阅读全文
posted @ 2019-02-12 17:46 hzhang_NJU 阅读(214) 评论(0) 推荐(0) 编辑
摘要: 1. Why Tensorflow 1. key idea: For a framework to be useful in production : it needs to be efficient, scalable, and maintainable . For research : the 阅读全文
posted @ 2019-02-12 17:44 hzhang_NJU 阅读(232) 评论(0) 推荐(0) 编辑
摘要: 1. 基本特点 1.1 save computation(惰性运行) 如上,因为 不需要用到 ,所以 的运算不会被执行(save computation) 1.2 Distributed Computation 1. 大图分解为子图多GPU并行计算, e.g. freamework举例 2. Mul 阅读全文
posted @ 2019-02-12 17:36 hzhang_NJU 阅读(219) 评论(0) 推荐(0) 编辑