얼굴, 포즈, 손의 랜드마크를 쉽게 가져오기위한 모듈
Project description
PyAutoMakerHuman
사람과 관련된 자동화 모듈
주의
이 프로젝트는 아직 개발중입니다 내보내는 API는 언제든지 바뀔 수 있습니다
설치
pip install PyAutoMakerHuman
또는
git clone https://github.com/boa9448/PyAutoMakerHuman.git
cd PyAutoMakerHuman
python setup.py install
사용
데이터셋 폴더 구조
dataset
├─face
└─hand
├─paper
├─rock
└─scissors
분류기 학습
import os
import PyAutoMakerHuman as pamh
#데이터셋 경로 지정
dataset_path = os.path.join("dataset", "hand")
#손 검출 임계치 0.7
hand = pamh.HandUtil(min_detection_confidence=0.7)
#데이터셋의 경로를 넘겨주면 사전형 값을 리턴함
data = hand.extract_dataset(dataset_path)
train_data, name = data["data"], data["name"]
trainer = pamh.SvmUtil()
#svm 학습
trainer.train_svm(train_data, name)
#학습된 svm 모델을 myModel폴더에 저장
trainer.save_svm("myModel")
이미지에서 손모양 분류
import cv2
import imutils
import os
import PyAutoMakerHuman as pamh
import random
hand = pamh.HandUtil(min_detection_confidence=0.7)
trainer = pamh.SvmUtil()
#학습된 svm모델을 불러옴
#myModel폴더에 있는 모델과 라벨을 불러옴
trainer.load_svm("myModel")
#이미지를 읽어옴
img_path = "test.jpg"
img = cv2.imread(img_path)
#이미지 리사이즈
img = imutils.resize(img, width=600)
#이미지에서 박스와 랜드마크를 추출함
data_list = hand.extract(img)
color_dict = {}
#이미지에서 탐지를 성공했다면...
if data_list:
for idx, data in enumerate(data_list):
landmark_1d = data[1]
name, proba = trainer.predict([landmark_1d])
box = data[0]
color = (0, 0, 0)
if name in color_dict:
color = color_dict[name]
else:
color = (random.randint(0, 255), random.randint(0, 255), random.randint(0, 255))
color_dict[name] = color
cv2.putText(img, f"{name} : {proba:.2f}", (box[0], box[1] - 25)
, cv2.FONT_HERSHEY_SIMPLEX, 1, color, 2, cv2.LINE_AA)
cv2.rectangle(img, (box[0], box[1]), (box[0] + box[2], box[1] + box[3])
, color, 2)
cv2.imshow("view", img)
cv2.waitKey()
cv2.destroyAllWindows()
추후 개발
간단하게 모델을 학습 시킬 수 있는 GUI도구
GUI도구 미리 둘러보기
패키지 설치 후 python -m PyAutoMakerHuman
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file PyAutoMakerHuman-1.2.1.tar.gz.
File metadata
- Download URL: PyAutoMakerHuman-1.2.1.tar.gz
- Upload date:
- Size: 47.9 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.1 importlib_metadata/4.6.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.61.2 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
55ce2b8c97918298973746074b3ce95fbb2845a6f7ae6116ad51dd5fc3285f69
|
|
| MD5 |
c823bcfcf4fa9fb1bf1eea82c5a54d74
|
|
| BLAKE2b-256 |
3b526047ececbb988012cfdccd5e608410399d630653a38941abd81969aefb86
|
File details
Details for the file PyAutoMakerHuman-1.2.1-py3-none-any.whl.
File metadata
- Download URL: PyAutoMakerHuman-1.2.1-py3-none-any.whl
- Upload date:
- Size: 47.9 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.1 importlib_metadata/4.6.1 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.61.2 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
fb20641792a4bfef2e9900a189f6c27b3c192c7e5cae5798351bc6c32560283d
|
|
| MD5 |
5cd08a5df46226ae2e68a7e947b4aefd
|
|
| BLAKE2b-256 |
ff3a9b41720dde0638435d04f732ba382e859bc3f25b2fad28bf8e6f3797262a
|