# YOLOv4
This is PyTorch implementation of [YOLOv4](https://github.com/AlexeyAB/darknet) which is based on [ultralytics/yolov3](https://github.com/ultralytics/yolov3).
* [[original Darknet implementation of YOLOv4]](https://github.com/AlexeyAB/darknet)
* [[ultralytics/yolov5 based PyTorch implementation of YOLOv4]](https://github.com/WongKinYiu/PyTorch_YOLOv4/tree/u5).
### development log
<details><summary> <b>Expand</b> </summary>
* `2021-10-31` - support [RS loss](https://arxiv.org/abs/2107.11669), [aLRP loss](https://arxiv.org/abs/2009.13592), [AP loss](https://arxiv.org/abs/2008.07294).
* `2021-10-30` - support [alpha IoU](https://arxiv.org/abs/2110.13675).
* `2021-10-20` - design resolution calibration methods.
* `2021-10-15` - support joint detection, instance segmentation, and semantic segmentation. [`seg-yolo`]()
* `2021-10-13` - design ratio yolo.
* `2021-09-22` - pytorch 1.9 compatibility.
* `2021-09-21` - support [DIM](https://arxiv.org/abs/1808.06670).
* `2021-09-16` - support [Dynamic Head](https://arxiv.org/abs/2106.08322).
* `2021-08-28` - design domain adaptive training.
* `2021-08-22` - design re-balance models.
* `2021-08-21` - support [simOTA](https://arxiv.org/abs/2107.08430).
* `2021-08-14` - design approximation-based methods.
* `2021-07-27` - design new decoders.
* `2021-07-22` - support 1) decoupled head, 2) anchor-free, and 3) multi positives in [yolox](https://arxiv.org/abs/2107.08430).
* `2021-07-10` - design distribution-based implicit modeling.
* `2021-07-06` - support outlooker attention. [`volo`](https://arxiv.org/abs/2106.13112)
* `2021-07-06` - design self emsemble training method.
* `2021-06-23` - design cross multi-stage correlation module.
* `2021-06-18` - design cross stage cross correlation module.
* `2021-06-17` - support cross correlation module. [`ccn`](https://arxiv.org/abs/2010.12138)
* `2021-06-17` - support attention modules. [`cbam`](https://arxiv.org/abs/1807.06521) [`saan`](https://arxiv.org/abs/2010.12138)
* `2021-04-20` - support swin transformer. [`swin`](https://arxiv.org/abs/2103.14030)
* `2021-03-16` - design new stem layers.
* `2021-03-13` - design implicit modeling. [`nn`]() [`mf`]() [`lc`]()
* `2021-01-26` - support vision transformer. [`tr`](https://arxiv.org/abs/2010.11929)
* `2021-01-26` - design mask objectness.
* `2021-01-25` - design rotate augmentation.
* `2021-01-23` - design collage augmentation.
* `2021-01-22` - support [VoVNet](https://arxiv.org/abs/1904.09730), [VoVNetv2](https://arxiv.org/abs/1911.06667).
* `2021-01-22` - support [EIoU](https://arxiv.org/abs/2101.08158).
* `2021-01-19` - support instance segmentation. [`mask-yolo`]()
* `2021-01-17` - support anchor-free-based methods. [`center-yolo`]()
* `2021-01-14` - support joint detection and classification. [`classify-yolo`]()
* `2020-01-02` - design new [PRN](https://github.com/WongKinYiu/PartialResidualNetworks) and [CSP](https://github.com/WongKinYiu/CrossStagePartialNetworks)-based models.
* `2020-12-22` - support transfer learning.
* `2020-12-18` - support non-local series self-attention blocks. [`gc`](https://arxiv.org/abs/1904.11492) [`dnl`](https://arxiv.org/abs/2006.06668)
* `2020-12-16` - support down-sampling blocks in cspnet paper. [`down-c`]() [`down-d`](https://arxiv.org/abs/1812.01187)
* `2020-12-03` - support imitation learning.
* `2020-12-02` - support [squeeze and excitation](https://arxiv.org/abs/1709.01507).
* `2020-11-26` - support multi-class multi-anchor joint detection and embedding.
* `2020-11-25` - support [joint detection and embedding](https://arxiv.org/abs/1909.12605). [`track-yolo`]()
* `2020-11-23` - support teacher-student learning.
* `2020-11-17` - pytorch 1.7 compatibility.
* `2020-11-06` - support inference with initial weights.
* `2020-10-21` - fully supported by darknet.
* `2020-09-18` - design fine-tune methods.
* `2020-08-29` - support [deformable kernel](https://arxiv.org/abs/1910.02940).
* `2020-08-25` - pytorch 1.6 compatibility.
* `2020-08-24` - support channel last training/testing.
* `2020-08-16` - design CSPPRN.
* `2020-08-15` - design deeper model. [`csp-p6-mish`]()
* `2020-08-11` - support [HarDNet](https://arxiv.org/abs/1909.00948). [`hard39-pacsp`]() [`hard68-pacsp`]() [`hard85-pacsp`]()
* `2020-08-10` - add DDP training.
* `2020-08-06` - support [DCN](https://arxiv.org/abs/1703.06211), [DCNv2](https://arxiv.org/abs/1811.11168). [`yolov4-dcn`]()
* `2020-08-01` - add pytorch hub.
* `2020-07-31` - support [ResNet](https://arxiv.org/abs/1512.03385), [ResNeXt](https://arxiv.org/abs/1611.05431), [CSPResNet](https://github.com/WongKinYiu/CrossStagePartialNetworks), [CSPResNeXt](https://github.com/WongKinYiu/CrossStagePartialNetworks). [`r50-pacsp`]() [`x50-pacsp`]() [`cspr50-pacsp`]() [`cspx50-pacsp`]()
* `2020-07-28` - support [SAM](https://arxiv.org/abs/2004.10934). [`yolov4-pacsp-sam`]()
* `2020-07-24` - update api.
* `2020-07-23` - support CUDA accelerated Mish activation function.
* `2020-07-19` - support and training tiny YOLOv4. [`yolov4-tiny`]()
* `2020-07-15` - design and training conditional YOLOv4. [`yolov4-pacsp-conditional`]()
* `2020-07-13` - support [MixUp](https://arxiv.org/abs/1710.09412) data augmentation.
* `2020-07-03` - design new stem layers.
* `2020-06-16` - support floating16 of GPU inference.
* `2020-06-14` - convert .pt to .weights for darknet fine-tuning.
* `2020-06-13` - update multi-scale training strategy.
* `2020-06-12` - design scaled YOLOv4 follow [ultralytics](https://github.com/ultralytics/yolov5). [`yolov4-pacsp-s`]() [`yolov4-pacsp-m`]() [`yolov4-pacsp-l`]() [`yolov4-pacsp-x`]()
* `2020-06-07` - design [scaling methods](https://github.com/WongKinYiu/PyTorch_YOLOv4/blob/master/images/scalingCSP.png) for CSP-based models. [`yolov4-pacsp-25`]() [`yolov4-pacsp-75`]()
* `2020-06-03` - update COCO2014 to COCO2017.
* `2020-05-30` - update FPN neck to CSPFPN. [`yolov4-yocsp`]() [`yolov4-yocsp-mish`]()
* `2020-05-24` - update neck of YOLOv4 to CSPPAN. [`yolov4-pacsp`]() [`yolov4-pacsp-mish`]()
* `2020-05-15` - training YOLOv4 with Mish activation function. [`yolov4-yospp-mish`]() [`yolov4-paspp-mish`]()
* `2020-05-08` - design and training YOLOv4 with [FPN](https://arxiv.org/abs/1612.03144) neck. [`yolov4-yospp`]()
* `2020-05-01` - training YOLOv4 with Leaky activation function using PyTorch. [`yolov4-paspp`]() [`PAN`](https://arxiv.org/abs/1803.01534)
</details>
## Pretrained Models & Comparison
| Model | Test Size | AP<sup>test</sup> | AP<sub>50</sub><sup>test</sup> | AP<sub>75</sub><sup>test</sup> | AP<sub>S</sub><sup>test</sup> | AP<sub>M</sub><sup>test</sup> | AP<sub>L</sub><sup>test</sup> | cfg | weights |
| :-- | :-: | :-: | :-: | :-: | :-: | :-: | :-: | :-: | :-: |
| **YOLOv4** | 640 | 50.0% | 68.4% | 54.7% | 30.5% | 54.3% | 63.3% | [cfg](https://github.com/WongKinYiu/PyTorch_YOLOv4/blob/master/cfg/yolov4.cfg) | [weights](https://drive.google.com/file/d/1TSvLHH48eJJk7Glr5p2lscVet2jCazhi/view?usp=sharing) |
| | | | | | | |
| **YOLOv4**<sub>pacsp-s</sub> | 640 | 39.0% | 57.8% | 42.4% | 20.6% | 42.6% | 50.0% | [cfg](https://github.com/WongKinYiu/PyTorch_YOLOv4/blob/master/cfg/yolov4-csp-s-leaky.cfg) | [weights](https://drive.google.com/file/d/1r1zeY8whdZNUGisxiZQFnbwYSIolCAwi/view?usp=sharing) |
| **YOLOv4**<sub>pacsp</sub> | 640 | 49.8% | 68.4% | 54.3% | 30.1% | 54.0% | 63.4% | [cfg](https://github.com/WongKinYiu/PyTorch_YOLOv4/blob/master/cfg/yolov4-csp-leaky.cfg) | [weights](https://drive.google.com/file/d/1W_zrTbCmctTgnv6BSjmNDJ3xGdKye4sw/view?usp=sharing) |
| **YOLOv4**<sub>pacsp-x</sub> | 640 | **52.2%** | **70.5%** | **56.8%** | **32.7%** | **56.3%** | **65.9%** | [cfg](https://github.com/WongKinYiu/PyTorch_YOLOv4/blob/master/cfg/yolov4-csp-x-leaky.cfg) | [weights](https://drive.google.com/file/d/1jL9727DVG2-iirG9EWRtAsa4vFei-L35/view?usp=sharing) |
| | | | | | | |
| **YOLOv4**<sub>pacsp-s-mish</sub> | 640 | 40.8% | 59.5% | 44.3% | 22.4% | 44.6% | 51.8% | [cfg](https://github.com/WongKinYiu/PyTorch_YOLOv4/blob/m
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
YOLOv4是由Alexey Bochkovskiy等人开发的目标检测模型,它是YOLO(You Only Look Once)系列中的第四个主要版本。YOLO系列因其速度快和性能好而受到广泛欢迎,适用于需要实时目标检测的场景。 以下是YOLOv4的一些关键特性和改进点: 性能提升:YOLOv4在速度和准确性上都有所提升,特别是在MS COCO数据集上,与其他目标检测模型相比,它在保持较高速度的同时,也达到了较高的准确率。 模型架构:YOLOv4采用了改进的模型架构,包括 CSP(Cross Stage Partial Network)技术,该技术可以减少计算量,同时保持检测性能。 数据增强:YOLOv4引入了多种数据增强技术,如mosaic数据增强和MixUp数据增强,这些技术有助于提高模型的泛化能力。 损失函数:YOLOv4使用了CIoU(Complete Intersection over Union)损失函数来替代传统的IoU(Intersection over Union)损失函数,CIoU损失函数考虑了边界框的中心点距离和宽高比,有助于提高边界框预测的准确性。
资源推荐
资源详情
资源评论
收起资源包目录
PyTorch_YOLOv4-master.zip (67个子文件)
PyTorch_YOLOv4-master
weights
put your weights file here.txt 70B
data
hyp.scratch.s.yaml 1KB
get_coco2014.sh 824B
coco.data 91B
samples
zidane.jpg 165KB
bus.jpg 476KB
coco16.data 77B
coco1cls.txt 672B
coco1cls.data 80B
coco1.data 75B
coco64.txt 3KB
coco64.data 77B
coco.yaml 1KB
coco2017.data 87B
coco1.txt 42B
coco2014.data 85B
coco16.txt 672B
get_coco2017.sh 824B
coco_paper.names 702B
hyp.scratch.yaml 1KB
coco.names 621B
utils
evolve.sh 932B
utils.py 41KB
__init__.py 1B
google_utils.py 5KB
parse_config.py 3KB
loss.py 7KB
metrics.py 5KB
gcp.sh 2KB
autoanchor.py 7KB
layers.py 13KB
general.py 18KB
activations.py 2KB
plots.py 15KB
datasets.py 54KB
adabound.py 11KB
torch_utils.py 9KB
requirements.txt 115B
models
export.py 3KB
models.py 32KB
detect.py 8KB
images
scalingCSP.png 315KB
cfg
yolov4-pacsp-x-mish.cfg 15KB
yolov4-pacsp-s.cfg 8KB
yolov4-csp-x-leaky.cfg 16KB
yolov4-csp-mish.cfg 14KB
yolov4-csp-leaky.cfg 14KB
yolov4-pacsp-s-mish.cfg 8KB
yolov4-pacsp-mish.cfg 13KB
yolov4-pacsp-x.cfg 15KB
yolov4-csp-s-leaky.cfg 9KB
yolov4-pacsp.cfg 13KB
yolov4-csp-s-mish.cfg 9KB
yolov4.cfg 12KB
yolov4-csp-x-mish.cfg 16KB
yolov4-paspp.cfg 12KB
yolov4-tiny.cfg 3KB
train.py 32KB
test.py 16KB
README.md 18KB
.idea
workspace.xml 2KB
misc.xml 188B
inspectionProfiles
Project_Default.xml 1KB
profiles_settings.xml 174B
modules.xml 301B
.gitignore 184B
PyTorch_YOLOv4-master.iml 452B
共 67 条
- 1
资源评论
张飞飞飞飞飞
- 粉丝: 372
- 资源: 26
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功