Giter Site home page Giter Site logo

heiheihelix / pytorch-learning-notes Goto Github PK

View Code? Open in Web Editor NEW

This project forked from panjinquan/pytorch-learning-notes

0.0 0.0 0.0 584.91 MB

pytorch learning tutorials

Python 5.00% Lua 0.01% Jupyter Notebook 0.37% Java 19.94% Makefile 0.05% C++ 64.67% HTML 0.08% CMake 3.02% C 6.76% Objective-C 0.11% Batchfile 0.01%

pytorch-learning-notes's Introduction

pytorch-learning-tutorials

觉得可以,麻烦给个”Star“

1.image_classification 图像分类

《pytorch实现L2和L1正则化的方法》https://panjinquan.blog.csdn.net/article/details/88426648

2.object_detection目标检测

mobileNet v1 v2 SSD目标检测:该项目是参考《pytorch-ssd》https://github.com/qfgaohao/pytorch-ssd ,修改,主要是方便训练。
数据集VOC2007和VOC2012:
训练方法:my_train_ssd.py
修改my_train_ssd.py的参数train_filename和val_filename即可,直接运行训练,例如:

train_filename = 'E:/git/VOC0712_dataset/train.txt' #训练文件
val_filename = 'E:/git/VOC0712_dataset/val.txt'     #测试文件

测试方法:run_ssd_example.py

net_type = 'mb2-ssd-lite' #模型类型
model_path = 'models/mb2-ssd-lite-Epoch-190-Loss-3.0529016691904802.pth'#模型路径
label_path = 'models/voc-model-labels.txt'#label文件路径
image_path = './dataset/images/6.jpg'#测试图片

3.DeepLearningTutorials教程

网上收集的Pytorch的学习资料

4.caffe2-android

在android上运行caffe2模型实现图像识别的demo

5.UNet图像分割

使用UNet模型实现的图像分割

一点笔记

查看GPU使用情况

nvidia-smi

指定使用GPU:

import os
os.environ["CUDA_VISIBLE_DEVICES"] = "1"#编号从0开始

pytorch版本,检查GPU是否可用

import torch
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
# device='cuda'
print("-----device:{}".format(device))
print("-----Pytorch version:{}".format(torch.__version__))

4.相关说明

Pytorch version:1.0.0

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.