GithubHelp home page GithubHelp logo

xiaotudui / pytorch-tutorial Goto Github PK

View Code? Open in Web Editor NEW
2.3K 2.3K 561.0 3.02 MB

PyTorch深度学习快速入门教程(绝对通俗易懂!)

Home Page: https://www.bilibili.com/video/av74281036

Python 100.00%
pytorch pytorch-tutorial

pytorch-tutorial's Introduction

Pytorch教程

相信尝试找到此教程的你,已经知道 PyTorch 的用途。

找到此教程的你,也许跟我一样,尝试过各种教程,官方的教程文档,各色的视频,但发现都不是很友好。

深知此感受的我,尝试写下这份教程,希望能为你稍微照亮下周边的道路。


零:如何使用

本系列教程,致力于打造成为通俗易懂的教程。所以课程安排的思路也是比较特点,相信一定能让你快速入门。

本文提供视频版(已完结)。(欢迎各位 Fork 和 Star)

视频中涉及的代码均在src文件夹中。

视频版:

Bilibili

Youtube


微信公众号:【我是土堆】

我的大本营,会不定期更新一些碎碎念,欢迎关注

往期推荐:

学会这三个排版原则,你就能超过80%人的排版

你想过将你的人生游戏化吗?

用游戏的思路激励自己

寻找有趣或更有效率的事、工具和教程

pytorch-tutorial's People

Contributors

xiaotudui avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

pytorch-tutorial's Issues

train.py训练时,loss出现Nan值

/opt/anaconda3/envs/pytorch/bin/python /Users/zth/PycharmProjects/pytorchFastTutorial/train.py
Files already downloaded and verified
Files already downloaded and verified
训练数据集的长度为:50000
测试数据集的长度为:10000
-------第 1 轮训练开始------
/opt/anaconda3/envs/pytorch/lib/python3.8/site-packages/torch/nn/functional.py:718: UserWarning: Named tensors and all their associated APIs are an experimental feature and subject to change. Please do not use them for anything important until they are released as stable. (Triggered internally at  /Users/distiller/project/conda/conda-bld/pytorch_1623459044803/work/c10/core/TensorImpl.h:1156.)
  return torch.max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode)
训练次数:100, Loss:1.9817659854888916
训练次数:200, Loss:1.9057204723358154
训练次数:300, Loss:1.7302981615066528
训练次数:400, Loss:1.5506035089492798
训练次数:500, Loss:1.6042922735214233
训练次数:600, Loss:2.496931314468384
训练次数:700, Loss:1.6171432733535767
整体测试集上的Loss: 262.62046909332275
整体测试集上的正确率: 0.3889999985694885
模型已保存
-------第 2 轮训练开始------
训练次数:800, Loss:1.2562278509140015
训练次数:900, Loss:1.1422173976898193
训练次数:1000, Loss:1.416947603225708
训练次数:1100, Loss:1.4992238283157349
训练次数:1200, Loss:1.331336259841919
训练次数:1300, Loss:1.245829463005066
训练次数:1400, Loss:1.0655444860458374
训练次数:1500, Loss:1.2835123538970947
整体测试集上的Loss: 230.35630249977112
整体测试集上的正确率: 0.4925000071525574
模型已保存
-------第 3 轮训练开始------
训练次数:1600, Loss:1.0310918092727661
训练次数:1700, Loss:1.0611821413040161
训练次数:1800, Loss:1.0310254096984863
训练次数:1900, Loss:1.144779086112976
训练次数:2000, Loss:1.2882472276687622
训练次数:2100, Loss:0.9842464327812195
训练次数:2200, Loss:0.7923548221588135
训练次数:2300, Loss:1.1152539253234863
整体测试集上的Loss: 256.62166798114777
整体测试集上的正确率: 0.4763999879360199
模型已保存
-------第 4 轮训练开始------
训练次数:2400, Loss:1.2120356559753418
训练次数:2500, Loss:0.9000757336616516
训练次数:2600, Loss:1.05060613155365
训练次数:2700, Loss:1.0712412595748901
训练次数:2800, Loss:1.121010184288025
训练次数:2900, Loss:nan
训练次数:3000, Loss:nan
训练次数:3100, Loss:nan
整体测试集上的Loss: nan
整体测试集上的正确率: 0.10000000149011612
模型已保存
-------第 5 轮训练开始------
训练次数:3200, Loss:nan
训练次数:3300, Loss:nan
训练次数:3400, Loss:nan
训练次数:3500, Loss:nan
训练次数:3600, Loss:nan
训练次数:3700, Loss:nan
训练次数:3800, Loss:nan
训练次数:3900, Loss:nan
整体测试集上的Loss: nan
整体测试集上的正确率: 0.10000000149011612
模型已保存
-------第 6 轮训练开始------
训练次数:4000, Loss:nan
训练次数:4100, Loss:nan
训练次数:4200, Loss:nan
训练次数:4300, Loss:nan
训练次数:4400, Loss:nan
训练次数:4500, Loss:nan
训练次数:4600, Loss:nan

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.