Skip to main content

WIDER-YOLO : Yüz Tespit Uygulaması Yap

Wider-Yolo Kütüphanesinin Kullanımı

1. Wider Face Veri Setini İndir

Not: İndirilen veri setini ismini değiştirmeden wider_data klasörün içine atın.

2. Dosyaları Düzeni:

datasets/ 
      wider_face_split/  
          - wider_face_train_bbx_gt.txt
          - wider_face_val_bbx_gt.txt
         
      WIDER_train/
         - images

      WIDER_train_annotations 

      WIDER_val
         - images

      WIDER_val_annotations

Not: WIDER_train_annotations ve WIDER_val_annotations klasörleri oluşturmanıza gerek yoktur.

3. Wider Veri Setini Voc Xml Formatına Çevir

python ./wider_to_xml.py -ap ./wider_data/wider_face_split/wider_face_train_bbx_gt.txt -tp ./wider_data/WIDER_train_annotations/ -ip ./wider_data/WIDER_train/images/
python ./wider_to_xml.py -ap ./wider_data/wider_face_split/wider_face_val_bbx_gt.txt -tp ./wider_data/WIDER_val_annotations/ -ip ./wider_data/WIDER_val/images/

4. Voc Xml Veri Setini Yolo Formatına Çevir

python ./xml_to_yolo --path ./wider_data/WIDER_train_annotations/
python ./xml_to_yolo --path ./wider_data/WIDER_val_annotations/

5. Yolo Modelini Eğit

!yolov5 train --data data.yaml --weights 'yolov5n.pt' --batch-size 16 --epochs 100 --imgs 512

6. Yolo Modelini Test Et

Tek resim test etmek için:

!yolov5 detect --weights wider-yolo.pth --source  file.jpg  

Tüm resim dosyasını test etmek için

!yolov5 detect --weights wider-yolo.pth --source  path/*.jpg 

Not: Yeterli Gpu kaynağına sahip olamadığım için wider seti için düşük parametre değerleri verdim. Parametre Değerleri:

batch-size: 256, epochs: 5, imgs 320

6. Yolov5 + Sahi Algoritmasını Test Et

from sahi.model import Yolov5DetectionModel
from sahi.utils.cv import read_image
from sahi.predict import get_prediction, get_sliced_prediction, predict
from IPython.display import Image

detection_model = Yolov5DetectionModel(
   model_path="last.pt",
   confidence_threshold=0.3,
   device="cpu",
)

result = get_sliced_prediction(
    "test_data/2.jpg",
    detection_model,
    slice_height = 256,
    slice_width = 256,
    overlap_height_ratio = 0.8,
    overlap_width_ratio = 0.8
)
result.export_visuals(export_dir="demo_data/")
Image("demo_data/prediction_visual.png")

Sahi Algoritması ile ilgili Örnek Proje:

Referanslar:

Metadata

Release files for wideryolo 0.0.8

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for wideryolo 0.0.8
File Size Uploaded
wideryolo-0.0.8.tar.gz 3.4 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for wideryolo 0.0.8
File Interpreter ABI Platform
wideryolo-0.0.8-py3-none-any.whl Python 3 none any Details

Total release size: 7.2 kB

Release files / wideryolo-0.0.8.tar.gz

Download URL wideryolo-0.0.8.tar.gz
Size 3.4 kB
Tags Source
SHA-256 checksum
How to use checksums
ef97971dc74a3def78a1c09ed190f7ba0d4cc59d706b82e7558af3397000ec3d
BLAKE2b-256 checksum
How to use checksums
cb390036e6648f9968a5a730b28928b48dfed8ea6142c6492d024499b453210b
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/3.7.1 importlib_metadata/4.10.0 pkginfo/1.8.2 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.9

Release files / wideryolo-0.0.8-py3-none-any.whl

Download URL wideryolo-0.0.8-py3-none-any.whl
Size 3.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
a4c2d4b49040c1b343df3c227bc242e4ddf77cc639b24f9c01226eb7b300cde6
BLAKE2b-256 checksum
How to use checksums
27dd82e4fe48bf96d4af3f624bd265bea4045ed7d461b2fb806a9424901a4ed1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/3.7.1 importlib_metadata/4.10.0 pkginfo/1.8.2 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.9

Release history Release notifications | RSS feed

This release

0.0.8 This release

2 release files

0.0.7

2 release files

0.0.6

1 release file

0.0.5

2 release files

0.0.3

1 release file

0.0.2

1 release file

0.0.1

1 release file

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page