• Tensorflow advanced notes — “2” — Introduction to computing


    Warm up flags Usage of flags: # filename:test.py import tensorflow as tf tf.flags.DEFINE_string(“train_image_dir”,”/tmp/train2014″,”Training image direct ory”) FLAGS = tf.flags.FLAGS print(FLAGS.train_image_dir) Output is /tmp/train2014 Generally speaking, this is to define variables, but tensorflow has the advantage of being very convenient, such as executing the following command python test.py –train_image_dir=”./train2014″ Output is ./train2014 placeholder tf.placeholder(dtype, shape=None, name=None) […]

  • Tensorflow end to end whirlwind tutorial


    Because at present, I am doing a project of equipment anomaly detection for my elder martial brother, and I began to have access to TF. This tutorial is not only the notes of this period, but also a quick index for other partners or latecomers of the project team. The so-called “end-to-end” refers to the […]

  • Python code practice of tensorflow in the environment of al.base-win10


    0. outline 0.1 infrastructure layer function assembly View layer Visualization of calculation chart TensorBoard Workflow layer Dataset preparation, storage, loading keras/TF Slim Calculation layer Construction of calculation graph and optimization of forward calculation / backward propagation TensorFlow Core 0.2 data flow graph The calculation graph (directed graph | data flow graph) describes the calculation process […]

  • Tensorflow advanced notes — “3” — about how to store image array in tfrecord


    Tfrecord is a data format provided by Google for in-depth learning. I think it’s very convenient, standardized and worth learning. This paper mainly talks about how to store array. Other data storage is relatively simple, just draw a few examples. Data in tfrecord needs a transformation process, which can be divided into three types int64 […]

  • Python multithreading implementation


    I started my first blog for beginners, recording every bit of learning, as a memo, and I hope to share with you. I hope you can correct the mistakes. I refer to the introduction of multithreading in python (http://www.cnblogs.com/fnng/p…), which is very introductory and detailed. This paper introduces the basic usage of threading. The simplest […]

  • (general) deep learning environment construction: tensorflow installation tutorial and common error resolution


    Different from the “handgrip” of other introductory tutorials, this article emphasizes “cause” rather than “effect”. The reason why I add “general” is that after you understand the development environment, you will not make those very low mistakes.We all know that deep learning involves a large number of models and algorithms. Looking at those messy formula […]

  • Introduction to MNIST machine learning


    When we start to learn programming, the first thing is often to learn to print “Hello world.”. It’s like getting started with programming with Hello world and getting started with machine learning with MNIST. MNIST is an entry-level computer vision data set, which contains a variety of handwritten digital pictures. It also contains the label […]

  • Learning notes tf059: natural language processing, intelligent chat robot


    Natural language processing, voice processing, text processing. Speech recognition enables the computer to “understand” human speech and “extract” the text information of speech. Japan’s Wells Fargo life insurance company spent $1.7 million to install artificial intelligence systems, convert text to customer language, and analyze positive or negative words. Intelligent customer service is the research focus […]

  • Learning note tf060: image and voice combination, speaking with pictures


    Professor Li Feifei, Artificial Intelligence Laboratory of Stanford University, realizes three elements of artificial intelligence: syntax, semantics and inference. Language, vision. By using Grammar (language grammar analysis, visual three-dimensional structure analysis) and semantics (language semantics, visual special action meaning) as model input training data, reasoning ability is realized, training learning ability is applied to work, […]

  • Learning note tf061: distributed tensorflow, distributed principles, best practices


    Distributed tensorflow is supported by the underlying technology of high performance grpc library. Martin Abadi, Ashish Agarwal, Paul Barham, tensorflow: large scale machine learning on heterogeneous distributed systems. Distributed principle. The distributed cluster consists of multiple server processes and client processes. Deployment mode: single machine multi card, distributed (multi machine multi card). The tensorflow is […]

  • Learning notes tf062: tensorflow linear algebra compilation framework XLA


    XLA (accelerated linear algebra), the main specific compiler in the field of linear algebra, optimizes tensorflow calculation. Just in time (JIT) compilation or ahead of time (AOT) compilation to implement XLA is helpful for hardware acceleration. XLA is still in the experimental stage. https://www.tensorflow.org/ve… 。 XLA advantage. Special compiler in the field of linear algebra, […]

  • Learning note tf063: tensorflow debugger


    Tensorflow debugger (tfdbg), a special debugger for tensorflow. The real-time data flow is displayed by breakpoints and computer graphics, and the internal structure and state of tensorflow graphics are visualized. It helps to train reasoning and debug model errors. https://www.tensorflow.org/pr… 。 Common error types, non numeric (Nan), infinite (INF). Tfdbg command line interface (CLI). Debugger […]