Git Product home page Git Product logo

yolo-lisa's People

Contributors

lilohuang avatar pjreddie avatar wyfsh 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

Watchers

 avatar  avatar  avatar

yolo-lisa's Issues

NaN

Hi Jianming Zhang, Manting Huang, Xiaokang Jin and Xudong Li,

I enjoyed reading your paper and I am impressed with the good work. My issue is this, when I use five anchor boxes, it works perfectly. When I use eight anchor boxes, after 250+ steps I experience NaNs. Have you experienced this? Do you have any understanding about why this could be occurring?

Thanks,

Trent

Where can I download the annotated data?

Hey, I actually was implementing Yolo for Traffic Sign Detection using LISA Dataset but it turns out that the dataset is fit for faster RCNN model. Can you please provide the annotations for YOLO model?

More information about the lisa.data and lisa.names files?

Hello, in the lisa.data file we can see that we have number of classes which is 6, but for the whole LISA data set of the traffic sign, we have 47 different type of the traffic signs. This information is from the categories.txt file of the LISA traffic sign dataset. Did you filter out the type of signs that you don't need? Would you mind provide more information about what are the traffic signs that you used for training? thank you.

question about the python tool

I have some questions about how to use the python tool to get the dataset format that we can use. In the lisa.names file we find there were 5 labels that we need:speedLimit, warning, noTurn, stop, pedestrianCrossing, signalAhead. I assume we need to use the extractAnnotations.py to get those annotations for the training and here is what I did
`:~/Desktop/CUelectrical car/DATASET/tools$ python extractAnnotations.py -c [speedLimit, noTurn, stop, pedestrainCrossing, signalAhead]

usage: extractAnnotations.py [-h] [-f acceptedTag] [-c category] [-m 5]
{copy,mark,blackout,crop} filename.csv

extractAnnotations.py: error: argument mode: invalid choice: 'noTurn,' (choose from 'copy', 'mark', 'blackout', 'crop')
`
Can you help me to find the way that I can convert the dataset into the format that I need? thank you!!

how to use cfg files to train YOLO-LISA model

./darknet detector train cfg/lisa.data cfg/yolo-lisa.cfg darknet19_448.conv.23

Excuse me, i am new to YOLO, am i doing right?
It prompts me an error with "Couldn't open file: LISATS/train/train.txt".

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.