Recently, I have released an anchor-free YOLO, inspired by YOLOX & YOLOv7:
https://github.com/yjh0410/FreeYOLO
This YOLO-Family project has been discontinued for updates and maintenance.
Recently, I rebuild my YOLO-Family project !!
- We recommend you to use Anaconda to create a conda environment:
conda create -n yolo python=3.6
- Then, activate the environment:
conda activate yolo
- Requirements:
pip install -r requirements.txt
PyTorch >= 1.1.0 and Torchvision >= 0.3.0
You can run following command to visualize positiva sample:
python train.py \
-d voc \
--root path/to/your/dataset \
-m yolov2 \
--batch_size 2 \
--vis_targets
My better YOLO family
In this project, you can enjoy:
- a new and stronger YOLOv1
- a new and stronger YOLOv2
- a stronger YOLOv3
- a stronger YOLOv3 with SPP
- a stronger YOLOv3 with DilatedEncoder
- YOLOv4 (I'm trying to make it better)
- YOLO-Tiny
- YOLO-Nano
- Try to make my YOLO-v4 better.
- Train my YOLOv1/YOLOv2 with ViT-Base (pretrained by MaskAutoencoder)
You can download all weights including my DarkNet-53, CSPDarkNet-53, MAE-ViT and YOLO weights from the following links.
My Backbone:
- DarkNet53: https://github.com/yjh0410/PyTorch_YOLO-Family/releases/download/yolo-weight/darknet53.pth
- CSPDarkNet-53: https://github.com/yjh0410/PyTorch_YOLO-Family/releases/download/yolo-weight/cspdarknet53.pth
- CSPDarkNet-Tiny: https://github.com/yjh0410/PyTorch_YOLO-Family/releases/download/yolo-weight/cspdarknet_tiny.pth
YOLOX-Backbone:
- CSPDarkNet-S: https://github.com/yjh0410/YOLOX-Backbone/releases/download/YOLOX-Backbone/yolox_cspdarknet_s.pth
- CSPDarkNet-M: https://github.com/yjh0410/YOLOX-Backbone/releases/download/YOLOX-Backbone/yolox_cspdarknet_m.pth
- CSPDarkNet-L: https://github.com/yjh0410/YOLOX-Backbone/releases/download/YOLOX-Backbone/yolox_cspdarknet_l.pth
- CSPDarkNet-X: https://github.com/yjh0410/YOLOX-Backbone/releases/download/YOLOX-Backbone/yolox_cspdarknet_x.pth
- CSPDarkNet-Tiny: https://github.com/yjh0410/YOLOX-Backbone/releases/download/YOLOX-Backbone/yolox_cspdarknet_tiny.pth
- CSPDarkNet-Nano: https://github.com/yjh0410/YOLOX-Backbone/releases/download/YOLOX-Backbone/yolox_cspdarknet_nano.pth
- YOLOv1: https://github.com/yjh0410/PyTorch_YOLO-Family/releases/download/yolo-weight/yolov1_35.22_54.7.pth
- YOLOv2: https://github.com/yjh0410/PyTorch_YOLO-Family/releases/download/yolo-weight/yolov2_36.4_56.6.pth
- YOLOv3: https://github.com/yjh0410/PyTorch_YOLO-Family/releases/download/yolo-weight/yolov3_36.9_59.0.pth
- YOLOv3-SPP: https://github.com/yjh0410/PyTorch_YOLO-Family/releases/download/yolo-weight/yolov3_spp_38.2_60.1.pth
- YOLOv3-DE: https://github.com/yjh0410/PyTorch_YOLO-Family/releases/download/yolo-weight/yolov3_de_38.7_60.2.pth
- YOLOv4: https://github.com/yjh0410/PyTorch_YOLO-Family/releases/download/yolo-weight/yolov4_exp_43.0_63.4.pth
- YOLO-Tiny: https://github.com/yjh0410/PyTorch_YOLO-Family/releases/download/yolo-weight/yolo_tiny_28.8_48.6.pth
- YOLO-Nano: https://github.com/yjh0410/PyTorch_YOLO-Family/releases/download/yolo-weight/yolo_nano_22.4_40.7.pth
Tricks in this project:
- Augmentations: Flip + Color jitter + RandomCrop
- Model EMA
- Mosaic Augmentation
- Multi Scale training
- Gradient accumulation
- MixUp Augmentation
- Cosine annealing learning schedule
- AdamW
- Scale loss by number of positive samples
All experiment results are evaluated on COCO val. All FPS results except YOLO-Nano's are measured on a 2080ti GPU. We will measure the speed of YOLO-Nano on a CPU.
FPS | AP | AP50 | AP75 | APs | APm | APl | GFLOPs | Params | |
YOLOv1-320 | 151 | 25.4 | 41.5 | 26.0 | 4.2 | 25.0 | 49.8 | 10.49 | 44.54M |
YOLOv1-416 | 128 | 30.1 | 47.8 | 30.9 | 7.8 | 31.9 | 53.3 | 17.73 | 44.54M |
YOLOv1-512 | 114 | 33.1 | 52.2 | 34.0 | 10.8 | 35.9 | 54.9 | 26.85 | 44.54M |
YOLOv1-640 | 75 | 35.2 | 54.7 | 37.1 | 14.3 | 39.5 | 53.4 | 41.96 | 44.54M |
YOLOv1-800 | 65.56 | 44.54M |
FPS | AP | AP50 | AP75 | APs | APm | APl | GFLOPs | Params | |
YOLOv2-320 | 147 | 26.8 | 44.1 | 27.1 | 4.7 | 27.6 | 50.8 | 10.53 | 44.89M |
YOLOv2-416 | 123 | 31.6 | 50.3 | 32.4 | 9.1 | 33.8 | 54.0 | 17.79 | 44.89M |
YOLOv2-512 | 108 | 34.3 | 54.0 | 35.4 | 12.3 | 37.8 | 55.2 | 26.94 | 44.89M |
YOLOv2-640 | 73 | 36.3 | 56.6 | 37.7 | 15.1 | 41.1 | 54.0 | 42.10 | 44.89M |
YOLOv2-800 | 65.78 | 44.89M |
FPS | AP | AP50 | AP75 | APs | APm | APl | GFLOPs | Params | |
YOLOv3-320 | 111 | 30.8 | 50.3 | 31.8 | 10.0 | 33.1 | 50.0 | 19.57 | 61.97M |
YOLOv3-416 | 89 | 34.8 | 55.8 | 36.1 | 14.6 | 37.5 | 52.9 | 33.08 | 61.97M |
YOLOv3-512 | 77 | 36.9 | 58.1 | 39.3 | 18.0 | 40.3 | 52.2 | 50.11 | 61.97M |
YOLOv3-608 | 51 | 37.0 | 58.9 | 39.3 | 20.5 | 41.2 | 49.0 | 70.66 | 61.97M |
YOLOv3-640 | 49 | 36.9 | 59.0 | 39.7 | 21.6 | 41.6 | 47.7 | 78.30 | 61.97M |
FPS | AP | AP50 | AP75 | APs | APm | APl | GFLOPs | Params | |
YOLOv3-SPP-320 | 110 | 31.0 | 50.8 | 32.0 | 10.5 | 33.0 | 50.4 | 19.68 | 63.02M |
YOLOv3-SPP-416 | 88 | 35.0 | 56.1 | 36.4 | 14.9 | 37.7 | 52.8 | 33.26 | 63.02M |
YOLOv3-SPP-512 | 75 | 37.2 | 58.7 | 39.1 | 19.1 | 40.0 | 53.0 | 50.38 | 63.02M |
YOLOv3-SPP-608 | 50 | 38.3 | 60.1 | 40.7 | 20.9 | 41.1 | 51.2 | 71.04 | 63.02M |
YOLOv3-SPP-640 | 48 | 38.2 | 60.1 | 40.4 | 21.6 | 41.1 | 50.5 | 78.72 | 63.02M |
The DilatedEncoder is proposed by YOLOF.
FPS | AP | AP50 | AP75 | APs | APm | APl | GFLOPs | Params | |
YOLOv3-DE-320 | 109 | 31.1 | 51.1 | 31.7 | 10.2 | 32.6 | 51.2 | 19.10 | 57.25M |
YOLOv3-DE-416 | 88 | 35.0 | 56.1 | 36.3 | 14.6 | 37.4 | 53.7 | 32.28 | 57.25M |
YOLOv3-DE-512 | 74 | 37.7 | 59.3 | 39.6 | 17.9 | 40.4 | 54.4 | 48.90 | 57.25M |
YOLOv3-DE-608 | 50 | 38.7 | 60.5 | 40.8 | 20.6 | 41.7 | 53.1 | 68.96 | 57.25M |
YOLOv3-DE-640 | 48 | 38.7 | 60.2 | 40.7 | 21.3 | 41.7 | 51.7 | 76.41 | 57.25M |
I'm still trying to make it better.
FPS | AP | AP50 | AP75 | APs | APm | APl | GFLOPs | Params | |
YOLOv4-320 | 89 | 39.2 | 58.6 | 40.9 | 16.9 | 44.1 | 59.2 | 16.38 | 58.14M |
YOLOv4-416 | 84 | 41.7 | 61.6 | 44.2 | 22.0 | 46.6 | 57.7 | 27.69 | 58.14M |
YOLOv4-512 | 70 | 42.9 | 63.1 | 46.1 | 24.5 | 48.3 | 56.5 | 41.94 | 58.14M |
YOLOv4-608 | 51 | 43.0 | 63.4 | 46.1 | 26.7 | 48.6 | 53.9 | 59.14 | 58.14M |
FPS | AP | AP50 | AP75 | APs | APm | APl | GFLOPs | Params | |
YOLO-Tiny-320 | 143 | 26.4 | 44.5 | 26.8 | 8.8 | 28.2 | 42.4 | 2.17 | 7.66M |
YOLO-Tiny-416 | 130 | 28.2 | 47.6 | 28.8 | 11.6 | 31.5 | 41.4 | 3.67 | 7.82M |
YOLO-Tiny-512 | 118 | 28.8 | 48.6 | 29.4 | 13.3 | 33.4 | 38.3 | 5.57 | 7.82M |
The FPS is measured on i5-1135G& CPU. Any accelerated deployments that would help speed up detection are not done.
FPS | AP | AP50 | AP75 | APs | APm | APl | GFLOPs | Params | |
YOLO-Nano-320 | 25 | 18.4 | 33.7 | 17.8 | 3.9 | 17.5 | 33.1 | 0.64 | 1.86M |
YOLO-Nano-416 | 15 | 21.4 | 38.5 | 20.9 | 6.5 | 21.4 | 34.8 | 0.99 | 1.86M |
YOLO-Nano-512 | 10 | 22.4 | 40.7 | 22.1 | 8.0 | 24.0 | 33.2 | 1.65 | 1.86M |
- BaiduYunDisk: https://pan.baidu.com/s/1tYPGCYGyC0wjpC97H-zzMQ Password:4la9
# specify a directory for dataset to be downloaded into, else default is ~/data/
sh data/scripts/VOC2007.sh # <directory>
# specify a directory for dataset to be downloaded into, else default is ~/data/
sh data/scripts/VOC2012.sh # <directory>
- BaiduYunDisk: https://pan.baidu.com/s/1xAPk8fnaWMMov1VEjr8-zA Password:6vhp
On Ubuntu system, you might use the command jar xvf xxx.zip
to unzip the train2017.zip
and test2017.zip
files
since they are larger than 2G (As far as I know, unzip
operation can't process the zip file which is larger than 2G.).
Just run sh data/scripts/COCO2017.sh
. You will get COCO train2017, val2017, test2017.
For example:
python train.py --cuda \
-d coco \
-m yolov1 \
-ms \
--ema \
--batch_size 16 \
--root path/to/dataset/
You can run python train.py -h
to check all optional argument. Or you can just run the shell file, for example:
sh train_yolov1.sh
If you have multi gpus like 8, and you put 4 images on each gpu:
python -m torch.distributed.launch --nproc_per_node=8 train.py -d coco \
--cuda \
-m yolov1 \
-ms \
--ema \
-dist \
--sybn \
--num_gpu 8 \
--batch_size 4 \
--root path/to/dataset/
Attention, --batch_size
is the number of batchsize on per GPU, not all GPUs.
I have upload all training log files. For example, 1-v1.txt
contains all the output information during the training YOLOv1.
It is strongly recommended that you open the training shell file to check how I train each YOLO detector.
For example:
python test.py -d coco \
--cuda \
-m yolov4 \
--weight path/to/weight \
--img_size 640 \
--root path/to/dataset/ \
--show
For example
python eval.py -d coco-val \
--cuda \
-m yolov1 \
--weight path/to/weight \
--img_size 640 \
--root path/to/dataset/
To run on COCO_test-dev(You must be sure that you have downloaded test2017):
python eval.py -d coco-test \
--cuda \
-m yolov1 \
--weight path/to/weight \
--img_size 640 \
--root path/to/dataset/
You will get a coco_test-dev.json
file.
Then you should follow the official requirements to compress it into zip format
and upload it the official evaluation server.