This repository is forked from PolygonObjectDetectin.
I added MS COCO trained weights.

This repository is based on Ultralytics/yolov5, with adjustments to enable polygon prediction boxes.

The codes are based on Ultralytics/yolov5, and several functions are added and modified to enable polygon prediction boxes.

The modifications compared with Ultralytics/yolov5 and their brief descriptions are summarized below:

1. data/polygon_ucas.yaml : Exemplar UCAS-AOD dataset to test the effects of polygon boxes

2. data/images/UCAS-AOD : For the inference of polygon-yolov5s-ucas.pt

3. models/common.py :
   3.1. class Polygon_NMS : Non-Maximum Suppression (NMS) module for Polygon Boxes
   3.2. class Polygon_AutoShape : Polygon Version of Original AutoShape, input-robust polygon model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and Polygon_NMS
   3.3. class Polygon_Detections : Polygon detections class for Polygon-YOLOv5 inference results

4. models/polygon_yolov5s_ucas.yaml : Configuration file of polygon yolov5s for exemplar UCAS-AOD dataset

5. models/yolo.py :
   5.1. class Polygon_Detect : Detect head for polygon yolov5 models with polygon box prediction
   5.2. class Polygon_Model : Polygon yolov5 models with polygon box prediction

6. utils/iou_cuda : CUDA extension for iou computation of polygon boxes
   6.1. extensions.cpp : CUDA extension file
   6.2. inter_union_cuda.cu : CUDA code for computing iou of polygon boxes
   6.3. setup.py : for building CUDA extensions module polygon_inter_union_cuda, with two functions polygon_inter_union_cuda and polygon_b_inter_union_cuda

7. utils/autoanchor.py :
   7.1. def polygon_check_anchors : Polygon version of original check_anchors
   7.2. def polygon_kmean_anchors : Create kmeans-evolved anchors from polygon-enabled training dataset, use minimum outter bounding box as approximations

8. utils/datasets.py :
   8.1. def polygon_random_perspective : Data augmentation for datasets with polygon boxes (augmentation effects: HSV-Hue, HSV-Saturation, HSV-Value, rotation, translation, scale, shear, perspective, flip up-down, flip left-right, mosaic, mixup)
   8.2. def polygon_box_candidates : Polygon version of original box_candidates
   8.3. class Polygon_LoadImagesAndLabels : Polygon version of original LoadImagesAndLabels
   8.4. def polygon_load_mosaic : Loads images in a 4-mosaic, with polygon boxes
   8.5. def polygon_load_mosaic9 : Loads images in a 9-mosaic, with polygon boxes
   8.6. def polygon_verify_image_label : Verify one image-label pair for polygon datasets
   8.7. def create_dataloader : Has been modified to include polygon datasets

9. utils/general.py :
   9.1. def xyxyxyxyn2xyxyxyxy : Convert normalized xyxyxyxy or segments into pixel xyxyxyxy or segments
   9.2. def polygon_segment2box : Convert 1 segment label to 1 polygon box label
   9.3. def polygon_segments2boxes : Convert segment labels to polygon box labels
   9.4. def polygon_scale_coords : Rescale polygon coords (xyxyxyxy) from img1_shape to img0_shape
   9.5. def polygon_clip_coords : Clip bounding polygon xyxyxyxy bounding boxes to image shape (height, width)
   9.6. def polygon_inter_union_cpu : iou computation (polygon) with cpu
   9.7. def polygon_box_iou : Compute iou of polygon boxes via cpu or cuda
   9.8. def polygon_b_inter_union_cpu : iou computation (polygon) with cpu for class Polygon_ComputeLoss in loss.py
   9.9. def polygon_bbox_iou : Compute iou of polygon boxes for class Polygon_ComputeLoss in loss.py via cpu or cuda
   9.10. def polygon_non_max_suppression : Runs Non-Maximum Suppression (NMS) on inference results for polygon boxes
   9.11. def polygon_nms_kernel : Non maximum suppression kernel for polygon-enabled boxes
   9.12. def order_corners : Return sorted corners for loss.py::class Polygon_ComputeLoss::build_targets

10. utils/loss.py :
    10.1. class Polygon_ComputeLoss : Compute loss for polygon boxes

11. utils/metrics.py :
    11.1. class Polygon_ConfusionMatrix : Polygon version of original ConfusionMatrix

12. utils/plots.py :
    12.1. def polygon_plot_one_box : Plot one polygon box on image
    12.2. def polygon_plot_one_box_PIL : Plot one polygon box on image via PIL
    12.3. def polygon_output_to_target : Convert model output to target format (batch_id, class_id, x1, y1, x2, y2, x3, y3, x4, y4, conf)
    12.4. def polygon_plot_images : Polygon version of original plot_images
    12.5. def polygon_plot_test_txt : Polygon version of original plot_test_txt
    12.6. def polygon_plot_targets_txt : Polygon version of original plot_targets_txt
    12.7. def polygon_plot_labels : Polygon version of original plot_labels

13. polygon_train.py : For training polygon-yolov5 models

14. polygon_test.py : For testing polygon-yolov5 models

15. polygon_detect.py : For detecting polygon-yolov5 models

16. requirements.py : Added python model shapely

1. build_targets in class Polygon_ComputeLoss & forward in class Polygon_Detect

For the CUDA extension to be successfully built without error, please use CUDA version >= 11.2. The codes have been verified in Ubuntu 16.04 with Tesla K80 GPU.

# The following codes install CUDA 11.2 from scratch on Ubuntu 16.04, if you have installed it, please ignore
# If you are using other versions of systems, please check https://tutorialforlinux.com/2019/12/01/how-to-add-cuda-repository-for-ubuntu-based-oses-2/
# Install Ubuntu kernel head
sudo apt install linux-headers-$(uname -r)

# Pinning CUDA repo
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64/cuda-ubuntu1604.pin
sudo mv cuda-ubuntu1604.pin /etc/apt/preferences.d/cuda-repository-pin-600

# Add CUDA GPG key
sudo apt-key adv --fetch-keys http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64/7fa2af80.pub

# Setting up CUDA repo
sudo add-apt-repository "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64/ /"

# Refresh apt repositories
sudo apt update

# Installing CUDA 11.2
sudo apt install cuda-11-2 -y
sudo apt install cuda-toolkit-11-2 -y

# Setting up path
echo 'export PATH=/usr/local/cuda-11.2/bin${PATH:+:${PATH}}' >> $HOME/.bashrc
# You are done installing CUDA 11.2

# Check NVIDIA
nvidia-smi
# Update all apts
sudo apt-get update
sudo apt-get -y upgrade

# Begin installing python 3.7
curl -o ~/miniconda.sh -O https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
chmod +x ~/miniconda.sh
./miniconda.sh -b
echo "PATH=~/miniconda3/bin:$PATH" >> ~/.bashrc 
source ~/.bashrc
conda install -y python=3.7
# You are done installing python

The following codes set you up with the Polygon Yolov5.

# clone git repo
git clone https://github.com/XinzeLee/PolygonObjectDetection
cd PolygonObjectDetection/polygon-yolov5
# install python package requirements
pip install -r requirements.txt
# install CUDA extensions
cd utils/iou_cuda
python setup.py install
# cd back to polygon-yolov5 folder
cd .. && cd ..

Try Polygon Yolov5s Model by Following Polygon-Tutorial 1

1. Inference

    $ python polygon_detect.py --weights polygon-yolov5s-ucas.pt --img 1024 --conf 0.75 \
        --source data/images/UCAS-AOD --iou-thres 0.4 --hide-labels

   

2. Test

    $ python polygon_test.py --weights polygon-yolov5s-ucas.pt --data polygon_ucas.yaml \
        --img 1024 --iou 0.65 --task val

   

3. Train

    $ python polygon_train.py --weights polygon-yolov5s-ucas.pt --cfg polygon_yolov5s_ucas.yaml \
        --data polygon_ucas.yaml --hyp hyp.ucas.yaml --img-size 1024 \
        --epochs 3 --batch-size 12 --noautoanchor --polygon --cache

4. Performance
   4.1. Confusion Matrix
   

   

   4.2. Precision Curve
   

   

   4.3. Recall Curve
   

   

   4.4. Precision-Recall Curve
   

   

   4.5. F1 Curve
   

   

Transform COCO Dataset to Polygon Labels by Following [Polygon-Tutorial 2](https://github.com/XinzeLee/PolygonObjectDetection/blob/main/polygon-yolov5/Polygon-Tutorial2.ipynb]

• ultralytics/yolov5
• NVIDIA/retinanet-examples
• ming71/yolov3-polygon

For 1 GPU(RTX A5000)

# Convert MS COCO to polygon format
python3 convert2polygon.py --input_dir path_to_coco --save

CUDA_VISIBLE_DEVICES=0 python3 polygon_train.py --weights "polygon-yolov5s-ucas.pt" \
    --cfg polygon_yolov5s_coco.yaml \
    --data polygon_coco.yaml --hyp data/hyp.ucas.yaml --img-size 640 \
    --epochs 300 --batch-size 40 --noautoanchor --polygon --name yolov5-s

CUDA_VISIBLE_DEVICES=0 python3 polygon_test.py --weights runs/train/yolov5-s/weights/polygon_best.pt \
    --data polygon_coco.yaml  --img 640  --iou 0.65 --conf-thres 0.1 --task val --batch-size 40 \
    --name yolov5-s 

CUDA_VISIBLE_DEVICES=0 python3 polygon_train.py --weights "" \
    --cfg polygon_yolov5l_coco.yaml \
    --data polygon_coco.yaml --hyp data/hyp.ucas.yaml --img-size 640 \
    --epochs 300 --batch-size 16 --noautoanchor --polygon --name yolov5-l

CUDA_VISIBLE_DEVICES=0 python3 polygon_test.py --weights runs/train/yolov5-l/weights/polygon_best.pt \
    --data polygon_coco.yaml  --img 640  --iou 0.65 --conf-thres 0.1 --task val --batch-size 16 \
    --name yolov5-l