Light

activatedgeek / lenet-5 Goto Github PK

View Code? Open in Web Editor NEW

211.0 4.0 93.0 11 KB

PyTorch implementation of LeNet-5 with live visualization

Python 100.00%

cnn pytorch convolutional-neural-networks lenet5 machine-learning deep-learning deep-neural-networks

lenet-5's Introduction

LeNet-5

This implements a slightly modified LeNet-5 [LeCun et al., 1998a] and achieves an accuracy of ~99% on the MNIST dataset.

Setup

Install all dependencies using the following command

$ pip install -r requirements.txt

Usage

Start the visdom server for visualization

$ python -m visdom.server

Start the training procedure

$ python run.py

See epoch train loss live graph at http://localhost:8097.

The trained model will be exported as ONNX to lenet.onnx. The lenet.onnx file can be viewed with Neutron

References

[1] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. "Gradient-based learning applied to document recognition." Proceedings of the IEEE, 86(11):2278-2324, November 1998.

lenet-5's People

Contributors

Stargazers

Watchers

Forkers

lee2839 haiminzhang hhppff wgqbit95 whu-dft wang21jun sgflower66 thgngu huanpass sanqiaiziji elapl mntabassm zhangjingsecond applesmiling excllent123 lianglili syedmahmoodneuron shayan-taheri bochuxt codedealer31 kowshikthopalli qiuqiu-lwf always-coder mengyao00 nosheensanay albertwdl dwang181 laiyurui tinaya524 xumin1993 drevicko jossome alexjung dudasdavid odibua shiwenyuene duguyue100 artificialzeng showgh456 yz6565785 wuwo007 seraphinaliang sadangelf chengjiacheng rguo12 boris081 karlinton mengshus wang837 lzjpaul liuwei1619 thhhomas mfrancies90 mxe191 explore16 songjiaming0729 tzq2doc messi-goat942 mzq308734881 funnymudpeee starrypath yys-polaris philw16 lixushenggis ritchiegit michelle20210106 fengbin2 mizhitian-xiaomi omid-ghozatlou alec-dawnlight cooper-ji junxnone malyang xuarehere shoaibmerajsami mickey910 gao1176325799 marvinx97 flix-dev sean-wade benjaminz12 sinferwu wyh-tch taming-wild-ai fradeet niu-shuo tomgao56 liuxy2318 chaolimao chenxy1986 hanjr92 zhongxu0528 zhjinjin

lenet-5's Issues

CrossEntropyLoss with LogSoftmax?

LeNet-5/lenet.py

Line 37 in b9d7f39

('sig7', nn.LogSoftmax(dim=-1))

I think there is no need to put LogSoftmax layer at the end of network if you are going to use CrossEntropyLoss ? Because CrossEntropyLoss combines nn.LogSoftmax() and nn.NLLLoss() in one single class.

OK FINE

请问一下，这个什么意思

F:\Git\LeNet-5>python run.py
Train - Epoch 1, Batch: 0, Loss: 2.312821
Traceback (most recent call last):
File "run.py", line 93, in
main()
File "run.py", line 89, in main
train_and_test(e)
File "run.py", line 83, in train_and_test
train(epoch)
File "run.py", line 58, in train
if viz.check_connection():
AttributeError: 'Visdom' object has no attribute 'check_connection'

Is it okay if I get rid of this line ？

thanks！

Recommend Projects

React

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

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

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

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
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.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

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

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.