yolor | Learn One Representation : Unified Network | Machine Learning library

by WongKinYiu Python Version: weights License: GPL-3.0

X-Ray Key Features Code Snippets(1)Community Discussions(1)Vulnerabilities Install Support

kandi X-RAY | yolor Summary

yolor is a Python library typically used in Artificial Intelligence, Machine Learning, Deep Learning, Pytorch applications. yolor has no bugs, it has no vulnerabilities, it has build file available, it has a Strong Copyleft License and it has medium support. You can download it from GitHub.

implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks. To reproduce the results in the paper, please use this branch. To reproduce the inference speed, please see darknet.

Support

Quality

Security

License

Reuse

Support

yolor has a medium active ecosystem.

It has 1888 star(s) with 532 fork(s). There are 32 watchers for this library.

It had no major release in the last 12 months.

There are 200 open issues and 73 have been closed. On average issues are closed in 38 days. There are 15 open pull requests and 0 closed requests.

It has a neutral sentiment in the developer community.

The latest version of yolor is weights

Quality

yolor has 0 bugs and 0 code smells.

Security

yolor has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

yolor code analysis shows 0 unresolved vulnerabilities.

There are 0 security hotspots that need review.

License

yolor is licensed under the GPL-3.0 License. This license is Strong Copyleft.

Strong Copyleft licenses enforce sharing, and you can use them when creating open source projects.

Reuse

yolor releases are available to install and integrate.

Build file is available. You can build the component from source.

Installation instructions, examples and code snippets are available.

It has 4428 lines of code, 242 functions and 19 files.

It has high code complexity. Code complexity directly impacts maintainability of the code.

Top functions reviewed by kandi - BETA

kandi has reviewed yolor and discovered the below as its top functions. This is intended to give you an instant insight into yolor implemented functionality, and help decide if they suit your requirements.

Train a trained model
Create a loader
Check if dataset exists
Context manager for torch distributed
Run darknet detection
Function to apply classification classification
Load a pretrained model
Forward computation
Create x y grid grids
Forward pass through x
Check anchors fit
Print mutation results to evolve
Create a daloader
Cache dataset labels
Plot evolution results in evolution
Prints information about the model
Fuse Conv2d layers
Plot test
Try to load a list of models
Fuse all layers in the model
Convert a yaml file to weights
Updates EMA parameters
Prune the given model
Check file existence
Check git status
Flattens a directory recursively
Get the most recent run

Get all kandi verified functions for this library.

yolor Key Features

No Key Features are available at this moment for yolor.

yolor Examples and Code Snippets

Model,Quick Start

Python

Lines of Code : 64

License : Permissive (MIT)

Copy

pip install -r requirements.txt

pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple

git clone https://github.com/xuarehere/yolovx_deepsort_pytorch.git

cd detector/YOLOv3/weight/
wget https://pjreddie.com/media/files/yolov3.

Community Discussions

Trending Discussions on yolor

CUDA: Out of memory error on 128 images dataset

QUESTION

CUDA: Out of memory error on 128 images dataset

Asked 2021-Jul-29 at 15:03

I'm trying to train YOLOR on coco128 dataset in Google Colab on coco128 dataset. The training set contains 112 images. The validation set contains 8 images. The testing set contains 8 images.

But, it throws cuda out of memory error. How could it be?? the dataset has only 128 images in total.

...

ANSWER

Answered 2021-Jul-29 at 15:03

vRAM usage has nothing to do with how many train/val examples there are, but rather model, image size, and batch size. 1280x1280 is a massive image size - on a 16gb GPU you will probably only be able to train at 1 or 2 batch size.

Either use a lower resolution/smaller model, a GPU with more vRAM, or decrease your batch size.

Also try NVIDIA AMP

Source https://stackoverflow.com/questions/68577169

Community Discussions, Code Snippets contain sources that include Stack Exchange Network

Vulnerabilities

No vulnerabilities reported

Install yolor

You can download it from GitHub.
You can use yolor like any standard Python library. You will need to make sure that you have a development environment consisting of a Python distribution including header files, a compiler, pip, and git installed. Make sure that your pip, setuptools, and wheel are up to date. When using pip it is generally recommended to install packages in a virtual environment to avoid changes to the system.

Support

For any new features, suggestions and bugs create an issue on GitHub. If you have any questions check and ask questions on community page Stack Overflow .

Find more information at: