https://feisky.xyz/machine-learning/tensorflow.html Recent content in Tensorflow on Machine Learning Hugo -- gohugo.io zh-cn https://feisky.xyz/machine-learning/tensorflow/kubeflow.html Mon, 01 Jan 0001 00:00:00 +0000 https://feisky.xyz/machine-learning/tensorflow/kubeflow.html Kubeflow 是 Google 发布的用于在 Kubernetes 集群中部署和管理 tensorflow 任务的框架。主要功能包括 用于管理 Jupyter 的 JupyterHub 服务 用于管理训练任务的 Tensorflow Training Controller 用于模型服务的 TF Serving 容器 部署 部署之前需 https://feisky.xyz/machine-learning/tensorflow/install.html Mon, 01 Jan 0001 00:00:00 +0000 https://feisky.xyz/machine-learning/tensorflow/install.html CPU 版 最简单的方法使用 pip 来安装 # Python 2.7 pip install --upgrade tensorflow # Python 3.x pip3 install --upgrade tensorflow docker 使用镜像 gcr.io/tensorflow/tensorflow 启动 CPU 版 Tensorflow： docker run -it -p 8888:8888 gcr.io/tensorflow/tensorflow 验证安装 $ python >>> import tensorflow as tf >>> hello = tf.constant('Hello, https://feisky.xyz/machine-learning/tensorflow/hello.html Mon, 01 Jan 0001 00:00:00 +0000 https://feisky.xyz/machine-learning/tensorflow/hello.html TensorFlow 安装 pip install tensorflow 或者在 docker 中 # CPU only docker run -it -p 8888:8888 tensorflow/tensorflow # GPU version nvidia-docker run -it -p 8888:8888 tensorflow/tensorflow:latest-gpu TensorFlow 入门 from __future__ import print_function, division import tensorflow as tf print('Loaded TF version', tf.__version__) 简单示例 import tensorflow as tf a = tf.constant(5, name="input_a") b = tf.constant(3, name="input_b") c = tf.mul(a, b, name="mul_c") d = tf.add(a, b, https://feisky.xyz/machine-learning/tensorflow/gpu.html Mon, 01 Jan 0001 00:00:00 +0000 https://feisky.xyz/machine-learning/tensorflow/gpu.html TensorFlow 支持 CPU 和 GPU 这两种设备，标识设备的方法为: “/cpu:0”: 机器中的 CPU “/gpu:0”: 机器中的 GPU, 如果你有一个的话. “/gpu:1”: 机器中的第二个 GPU, 以此类推… 记录设备指派情 https://feisky.xyz/machine-learning/tensorflow/deeplearning.html Mon, 01 Jan 0001 00:00:00 +0000 https://feisky.xyz/machine-learning/tensorflow/deeplearning.html Google Cloud Platform 推出了一个 “Learn TensorFlow and deep learning, without a Ph.D.” 的教程，介绍了如何基于 Tensorflow 实现 CNN 和 RNN，链接在 这里。 Youtube Slide1 Slide2 Sample Code 另外，完整版笔记见 这里。 https://feisky.xyz/machine-learning/tensorflow/distributed.html Mon, 01 Jan 0001 00:00:00 +0000 https://feisky.xyz/machine-learning/tensorflow/distributed.html 相关概念 客户端 (Client): 客户端是一个用于建立 TensorFlow 计算图并创立与集群进行交互的会话层 tensorflow::Session 的程序。一般客户端是通过 python 或 C++ 实现的。一个独立的客户端进程可以同时 https://feisky.xyz/machine-learning/tensorflow/debug.html Mon, 01 Jan 0001 00:00:00 +0000 https://feisky.xyz/machine-learning/tensorflow/debug.html See wookayin’s guide. https://feisky.xyz/machine-learning/tensorflow/go.html Mon, 01 Jan 0001 00:00:00 +0000 https://feisky.xyz/machine-learning/tensorflow/go.html Tensorflow For Go 支持 Linux 和 MacOS。 安装 下载动态链接库 $ TF_TYPE="cpu" # Change to "gpu" for GPU support $ TARGET_DIRECTORY='/usr/local' $ curl -L "https://storage.googleapis.com/tensorflow/libtensorflow/libtensorflow-${TF_TYPE}-$(go env GOOS)-x86_64-1.2.0.tar.gz" | sudo tar -C $TARGET_DIRECTORY -xz # Linux 上还需要执行 ldconfig $ sudo ldconfig 下载 Tensorflow Go 库 $ go get github.com/tensorflow/tensorflow/tensorflow/go 下载完成 https://feisky.xyz/machine-learning/tensorflow/getting-started.html Mon, 01 Jan 0001 00:00:00 +0000 https://feisky.xyz/machine-learning/tensorflow/getting-started.html Getting Started in TensorFlow A look at a very simple neural network in TensorFlow This is an introduction to working with TensorFlow. It works through an example of a very simple neural network, walking through the steps of setting up the input, adding operators, setting up gradient descent, and running the computation graph. A simple neural network Let’s start with code. We’re going to construct a very simple neural network computing a linear regression between two variables, y and x. https://feisky.xyz/machine-learning/tensorflow/gpu_list.html Mon, 01 Jan 0001 00:00:00 +0000 https://feisky.xyz/machine-learning/tensorflow/gpu_list.html 使用tensorflow查询GPU设备列表 from tensorflow.python.client import device_lib def get_all_gpus(): local_device_protos = device_lib.list_local_devices() return [x.name for x in local_device_protos if x.device_type == 'GPU'] print(get_all_gpus()) 注意：docker容器开启privileged参数后可以访 https://feisky.xyz/machine-learning/tensorflow/install-src.html Mon, 01 Jan 0001 00:00:00 +0000 https://feisky.xyz/machine-learning/tensorflow/install-src.html Tensorflow源码安装 以Ubuntu 16.04为例，介绍Tensorflow源码安装的方法。 下载tensorflow源码 git clone https://github.com/tensorflow/tensorflow 安装ba https://feisky.xyz/machine-learning/tensorflow/mnist-tutorial/readme.html Mon, 01 Jan 0001 00:00:00 +0000 https://feisky.xyz/machine-learning/tensorflow/mnist-tutorial/readme.html This repository was moved to github.com/GoogleCloudPlatform/tensorflow-without-a-phd/tensorflow-mnist-tutorial https://feisky.xyz/machine-learning/tensorflow/serve.html Mon, 01 Jan 0001 00:00:00 +0000 https://feisky.xyz/machine-learning/tensorflow/serve.html Tensorflow serving https://feisky.xyz/machine-learning/tensorflow/tensorboard.html Mon, 01 Jan 0001 00:00:00 +0000 https://feisky.xyz/machine-learning/tensorflow/tensorboard.html Start tensorboard tensorboard --logdir=logs/ Main Graph