Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (9.0%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: Fuyi-Ran
- License: agpl-3.0
- Language: C++
- Default Branch: main
- Size: 11.4 MB
Statistics
- Stars: 3
- Watchers: 0
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
docs/README.md
Yolov11
MutilBackbone-MSGA bifpn Yolo 100 mAP50 0.99 (RTX4090)
PyTorch 1.11.0
Python 3.8
CUDA 11.3
yolov11
- pywt
```python
(yolov11,)
conda activate yolov11
pip install PyWavelets ```
- ()
train.pydata.yamldata.yaml**** datasetsimageslabelstraintestval
Yolov11 lightweight improvements
By fusing the MutilBackbone-MSGA module and the bifpn module, Yolo face recognition has been changed to a light-weight model, and the improved program can complete 100 rounds of training with a dataset of more than 20,000 images in half an hour, and the average accuracy of the model mAP50 is stable at more than 0.99 (renting RTX4090 graphics card).
Configuration Environment:
PyTorch 1.11.0
Python 3.8
CUDA 11.3
Regular yolov11 operating environment is sufficient
Frequently asked questions:
- Error: There is no pywt module.
At this point, you only need to download the module in the environment.
```python
Activate the configuration environment first (My environment name is yolov11, you should replace it with your environment name when using it)
conda activate yolov11
Then install the module
pip install PyWavelets ```
To use the code, you need to change all the file paths involved in the code to the location of your files, mainly involving two files (both files are in the root directory): one is
train.py, you need to pay attention to the path replacement of thedata.yamlfile. The other is the path substitution of the training dataset in thedata.yamlfile. It is best to use absolute paths for all paths, not relative paths, to avoid the situation where the file cannot be found.To use this project to train your dataset, you need to replace the
datasetsfolder in the root directory with your dataset according to the format (the core part is thetrain,test, andvalfolders in theimagesfolder andlabelsfolder to be divided correctly).
Owner
- Login: Fuyi-Ran
- Kind: user
- Repositories: 1
- Profile: https://github.com/Fuyi-Ran
Citation (CITATION.cff)
# This CITATION.cff file was generated with https://bit.ly/cffinit
cff-version: 1.2.0
title: Ultralytics YOLO
message: >-
If you use this software, please cite it using the
metadata from this file.
type: software
authors:
- given-names: Glenn
family-names: Jocher
affiliation: Ultralytics
orcid: 'https://orcid.org/0000-0001-5950-6979'
- family-names: Qiu
given-names: Jing
affiliation: Ultralytics
orcid: 'https://orcid.org/0000-0003-3783-7069'
- given-names: Ayush
family-names: Chaurasia
affiliation: Ultralytics
orcid: 'https://orcid.org/0000-0002-7603-6750'
repository-code: 'https://github.com/ultralytics/ultralytics'
url: 'https://ultralytics.com'
license: AGPL-3.0
version: 8.0.0
date-released: '2023-01-10'
GitHub Events
Total
- Watch event: 3
- Push event: 2
- Create event: 2
Last Year
- Watch event: 3
- Push event: 2
- Create event: 2
Dependencies
- pytorch/pytorch 2.4.1-cuda12.1-cudnn9-runtime build
- transformers *
- ultralytics *
- matplotlib >=3.3.0
- numpy >=1.23.0
- opencv-python >=4.6.0
- pandas >=1.1.4
- pillow >=7.1.2
- psutil *
- py-cpuinfo *
- pyyaml >=5.3.1
- requests >=2.23.0
- scipy >=1.4.1
- seaborn >=0.11.0
- torch >=1.8.0
- torch >=1.8.0,!=2.4.0; sys_platform == 'win32'
- torchvision >=0.9.0
- tqdm >=4.64.0
- ultralytics-thop >=2.0.0
- causal_conv1d >=1.2.0
- einops *
- ninja *
- packaging *
- torch *
- transformers *
- triton *
- einops *
- ninja *
- packaging *
- torch *