Skip to main content

TSRCNN_Texture Synthesis with Rotation using CNN package

Project description

TSRCNN : Texture Synthesis with Rotation using CNN We improved the existing CNN texture synthesis technique by rotating the texture image to provide directionality.

How to use :

TSRCNN(image, rotateNum=8, outputScale=2, generateRotation = True, resultNameRotate="resultTextureImg", resultSave=False, Patch_before_limit=False, Patch_before_scale=120)

param image: 이미지 경로 - 필수 입력 (ex)"절대경로") param rotateNum: 360도(중심 기준)/n 만큼 회전시켜 총 n 개의 회전 예제 텍스처를 생성 (n=8개) param outputScale: 결과 이미지 사이즈 얼마나 배로 늘릴것인가 (2배) param generateRotation: 회전 예제 이미지를 생성할것인가? (True) - False 일 경우 기존 회전 예제 이미지 사용할 것을 대비. param resultNameRotate: 저장할 결과 이름 ("resultTextureImg"+".png") param resultSave: 결과를 저장할 것인가? (False) param Patch_before_limit: 초기 이미지 크기 제한 여부 (Flase) - 가로세로 길이가 모두 제한크기 이상 넘어갈 경우 제한크기로 크기조절 param Patch_before_scale: 초기 이미지 제한 크기 (120픽셀) - 클수록 합성 시간 오래 걸림

return: PIL image - Texture Synthesis result

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

TSRCNN-0.0.3.tar.gz (3.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

TSRCNN-0.0.3-py3-none-any.whl (4.1 kB view details)

Uploaded Python 3

File details

Details for the file TSRCNN-0.0.3.tar.gz.

File metadata

  • Download URL: TSRCNN-0.0.3.tar.gz
  • Upload date:
  • Size: 3.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.0.0 CPython/3.11.4

File hashes

Hashes for TSRCNN-0.0.3.tar.gz
Algorithm Hash digest
SHA256 8df2758a2b09c7aac5e5b407dfddc336f0e8e455e54b8289f7415be4bd5b139c
MD5 16c1fd7dbe032734db6bf18e5a543a48
BLAKE2b-256 743732aa00c4bfc0afb47a4671b5f8d635866c5cfebf07ec240470c4e53140bf

See more details on using hashes here.

File details

Details for the file TSRCNN-0.0.3-py3-none-any.whl.

File metadata

  • Download URL: TSRCNN-0.0.3-py3-none-any.whl
  • Upload date:
  • Size: 4.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.0.0 CPython/3.11.4

File hashes

Hashes for TSRCNN-0.0.3-py3-none-any.whl
Algorithm Hash digest
SHA256 5ce238761a1ffca63b2635b17080b7de9d50a66ac48b95c38600697d9fda99d0
MD5 6255177ad20c7b49f43ae5c8a4c8f768
BLAKE2b-256 0d7e6c97812638867e9794fce1d88106d88acffb5e2448a2f99ad4a0ec1820ed

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page