1. YOLOv7

The following is the official document of YOLOv7

1-1 YOLOv7 Official Document

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

Web Demo

Integrated into Huggingface Spaces 🤗 using Gradio. Try out the Web Demo

Performance

MS COCO

Model	Test Size	AP^test	AP₅₀^test	AP₇₅^test	batch 1 fps	batch 32 average time
YOLOv7	640	51.4%	69.7%	55.9%	161 fps	2.8 ms
YOLOv7-X	640	53.1%	71.2%	57.8%	114 fps	4.3 ms

YOLOv7-W6	1280	54.9%	72.6%	60.1%	84 fps	7.6 ms
YOLOv7-E6	1280	56.0%	73.5%	61.2%	56 fps	12.3 ms
YOLOv7-D6	1280	56.6%	74.0%	61.8%	44 fps	15.0 ms
YOLOv7-E6E	1280	56.8%	74.4%	62.1%	36 fps	18.7 ms

Installation

Docker environment (recommended)

Expand

# create the docker container, you can change the share memory size if you have more.
nvidia-docker run --name yolov7 -it -v your_coco_path/:/coco/ -v your_code_path/:/yolov7 --shm-size=64g nvcr.io/nvidia/pytorch:21.08-py3

# apt install required packages
apt update
apt install -y zip htop screen libgl1-mesa-glx

# pip install required packages
pip install seaborn thop

# go to code folder
cd /yolov7

Testing

yolov7.pt yolov7x.pt yolov7-w6.pt yolov7-e6.pt yolov7-d6.pt yolov7-e6e.pt

python test.py --data data/coco.yaml --img 640 --batch 32 --conf 0.001 --iou 0.65 --device 0 --weights yolov7.pt --name yolov7_640_val

You will get the results:

 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.51206
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.69730
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.55521
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.35247
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.55937
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.66693
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.38453
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.63765
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.68772
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.53766
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.73549
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.83868

To measure accuracy, download COCO-annotations for Pycocotools to the ./coco/annotations/instances_val2017.json

Training

Data preparation

bash scripts/get_coco.sh

Download MS COCO dataset images (train, val, test) and labels. If you have previously used a different version of YOLO, we strongly recommend that you delete train2017.cache and val2017.cache files, and redownload labels

Single GPU training

# train p5 models
python train.py --workers 8 --device 0 --batch-size 32 --data data/coco.yaml --img 640 640 --cfg cfg/training/yolov7.yaml --weights '' --name yolov7 --hyp data/hyp.scratch.p5.yaml

# train p6 models
python train_aux.py --workers 8 --device 0 --batch-size 16 --data data/coco.yaml --img 1280 1280 --cfg cfg/training/yolov7-w6.yaml --weights '' --name yolov7-w6 --hyp data/hyp.scratch.p6.yaml

Multiple GPU training

# train p5 models
python -m torch.distributed.launch --nproc_per_node 4 --master_port 9527 train.py --workers 8 --device 0,1,2,3 --sync-bn --batch-size 128 --data data/coco.yaml --img 640 640 --cfg cfg/training/yolov7.yaml --weights '' --name yolov7 --hyp data/hyp.scratch.p5.yaml

# train p6 models
python -m torch.distributed.launch --nproc_per_node 8 --master_port 9527 train_aux.py --workers 8 --device 0,1,2,3,4,5,6,7 --sync-bn --batch-size 128 --data data/coco.yaml --img 1280 1280 --cfg cfg/training/yolov7-w6.yaml --weights '' --name yolov7-w6 --hyp data/hyp.scratch.p6.yaml

Transfer learning

yolov7_training.pt yolov7x_training.pt yolov7-w6_training.pt yolov7-e6_training.pt yolov7-d6_training.pt yolov7-e6e_training.pt

Single GPU finetuning for custom dataset

# finetune p5 models
python train.py --workers 8 --device 0 --batch-size 32 --data data/custom.yaml --img 640 640 --cfg cfg/training/yolov7-custom.yaml --weights 'yolov7_training.pt' --name yolov7-custom --hyp data/hyp.scratch.custom.yaml

# finetune p6 models
python train_aux.py --workers 8 --device 0 --batch-size 16 --data data/custom.yaml --img 1280 1280 --cfg cfg/training/yolov7-w6-custom.yaml --weights 'yolov7-w6_training.pt' --name yolov7-w6-custom --hyp data/hyp.scratch.custom.yaml

Re-parameterization

See reparameterization.ipynb

Inference

On video:

python detect.py --weights yolov7.pt --conf 0.25 --img-size 640 --source yourvideo.mp4

On image:

python detect.py --weights yolov7.pt --conf 0.25 --img-size 640 --source inference/images/horses.jpg

Export

Pytorch to CoreML (and inference on MacOS/iOS)

Pytorch to ONNX with NMS (and inference)

python export.py --weights yolov7-tiny.pt --grid --end2end --simplify \
        --topk-all 100 --iou-thres 0.65 --conf-thres 0.35 --img-size 640 640 --max-wh 640

Pytorch to TensorRT with NMS (and inference)

wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-tiny.pt
python export.py --weights ./yolov7-tiny.pt --grid --end2end --simplify --topk-all 100 --iou-thres 0.65 --conf-thres 0.35 --img-size 640 640
git clone https://github.com/Linaom1214/tensorrt-python.git
python ./tensorrt-python/export.py -o yolov7-tiny.onnx -e yolov7-tiny-nms.trt -p fp16

Pytorch to TensorRT another way

Expand

wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-tiny.pt
python export.py --weights yolov7-tiny.pt --grid --include-nms
git clone https://github.com/Linaom1214/tensorrt-python.git
python ./tensorrt-python/export.py -o yolov7-tiny.onnx -e yolov7-tiny-nms.trt -p fp16

# Or use trtexec to convert ONNX to TensorRT engine
/usr/src/tensorrt/bin/trtexec --onnx=yolov7-tiny.onnx --saveEngine=yolov7-tiny-nms.trt --fp16

Tested with: Python 3.7.13, Pytorch 1.12.0+cu113

Pose estimation

code yolov7-w6-pose.pt

See keypoint.ipynb.

Instance segmentation

code yolov7-mask.pt

See instance.ipynb.

Instance segmentation

code yolov7-seg.pt

YOLOv7 for instance segmentation (YOLOR + YOLOv5 + YOLACT)

Model	Test Size	AP^box	AP₅₀^box	AP₇₅^box	AP^mask	AP₅₀^mask	AP₇₅^mask
YOLOv7-seg	640	51.4%	69.4%	55.8%	41.5%	65.5%	43.7%

Anchor free detection head

code yolov7-u6.pt

YOLOv7 with decoupled TAL head (YOLOR + YOLOv5 + YOLOv6)

Model	Test Size	AP^val	AP₅₀^val	AP₇₅^val
YOLOv7-u6	640	52.6%	69.7%	57.3%

Citation

@article{wang2022yolov7,
  title={{YOLOv7}: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors},
  author={Wang, Chien-Yao and Bochkovskiy, Alexey and Liao, Hong-Yuan Mark},
  journal={arXiv preprint arXiv:2207.02696},
  year={2022}
}

Acknowledgements

Expand

1-2 YOLOv7 Changes

Components

detect.py
- Creates a csv file containing information regarding the 'Ticker,Date,Label,Close,Probability,Range,Detect' for each individual stock.
draw.py
- Allows us to draw the box and label on an image if we have the according labeling/detect csv files

Getting Started

1. Clone Repository

git clone https://github.com/VAIV-SKKU/YOLO-Train.git

2. Add Custom Dataset path to kospiALL.yaml

train: [CUSTOM_TRAIN_DATASET_PATH]
val: [CUSTOM_VAL_DATASET_PATH]

3. Train the model

python train.py --workers 8 --device 0 --batch-size 32 --data data/[CUSTOM_FILE].yaml --img 640 640 --cfg cfg/training/yolov7.yaml --weights '' --name yolov7 --hyp data/hyp.scratch.p5.yaml

4. Use the weights from the trained model to run detect.py

python detect.py --save-txt --trace --weights [WEIGHTS_FROM_TRAINED_MODEL] --conf 0.8 --imgsz 640 --source [DETECT_IMAGE_FOLDER_PATH] --name '' --pair 0

Condition

Directory Condition To use module in Data Folder

├── Data
└── Yolo-Train

Image Folder Condition To convert pixel coordinate to date

{Image Folder}
├── images
│     └── ...
│         ├── 000250_2022-12-01_245.png
│         └── ...
└── pixels
      └── ...
          ├── 000250_2022-12-01_245.csv
          └── ...

Arguments

pair 0 : Detects both BUY/SELL signals
pair 1 : Only detects BUY signals & SELL price for five transaction days later
pair 2 : Only detects SELL signals
conf : Only detects signals above the inserted confidence score

Running detect.py results in creating the 'signal' folder of the recent 'runs' folder. The individual csv files for each stock are stored inside the 'signal' folder. We later use these csv files to calculate the annual profits.

runs
└── detect
      └── [DUMMY_RUN]
            ├── images
            ├── labels  
            ├── signals
                 ├── 000020.csv
                 └── ...

5. Calculate the annual profits

Calculate YOLO Profit

1-3 KOSPI50 YOLO Profit Test Results

Dataset:

Result:

Auto-sell after five transaction days
Sell when BUY/SELL pair is satisfied

1-4 Reference Papers

Paper link: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9092995

Github link: https://github.com/gunaytemur/With-Yolov3-Buy-Sell-on-Candlestick

Name		Name	Last commit message	Last commit date
Latest commit History 51 Commits
__pycache__		__pycache__
cfg		cfg
data		data
log		log
models		models
runs		runs
utils		utils
.gitmodules		.gitmodules
README.md		README.md
detect.bash		detect.bash
detect.py		detect.py
draw.py		draw.py
export.py		export.py
requirements.txt		requirements.txt
score.bash		score.bash
train.py		train.py
yolo_profit_upper20_arthmetic.py		yolo_profit_upper20_arthmetic.py

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Repository files navigation

1. YOLOv7

1-1 YOLOv7 Official Document

Web Demo

Performance

Installation

Testing

Training

Transfer learning

Re-parameterization

Inference

Export

Pose estimation

Instance segmentation

Instance segmentation

Anchor free detection head

Citation

Acknowledgements

1-2 YOLOv7 Changes

Components

Getting Started

1. Clone Repository

2. Add Custom Dataset path to kospiALL.yaml

3. Train the model

4. Use the weights from the trained model to run detect.py

Condition

Arguments

5. Calculate the annual profits

1-3 KOSPI50 YOLO Profit Test Results

1-4 Reference Papers

About

Releases

Packages

Contributors 3

Languages

VAIV-SKKU/YOLO-Train

Folders and files

Latest commit

History

Repository files navigation

1. YOLOv7

1-1 YOLOv7 Official Document

Web Demo

Performance

Installation

Testing

Training

Transfer learning

Re-parameterization

Inference

Export

Pose estimation

Instance segmentation

Instance segmentation

Anchor free detection head

Citation

Acknowledgements

1-2 YOLOv7 Changes

Components

Getting Started

1. Clone Repository

2. Add Custom Dataset path to kospiALL.yaml

3. Train the model

4. Use the weights from the trained model to run detect.py

Condition

Arguments

5. Calculate the annual profits

1-3 KOSPI50 YOLO Profit Test Results

1-4 Reference Papers

About

Resources

Stars

Watchers

Forks

Releases

Packages 0

Contributors 3

Languages

Packages