๐ฆ ๋ด์ผ๋ฐฐ์์บ ํ/TIL(Today I Learned) TIL_220623_๋ฅ๋ฌ๋ - ์ ํ์ ์ ํ๋ก์ ํธ Style transfer = ์ ๋ก๋ํ ์ฌ์ง์ ์ ํ์ฒ๋ผ ๋ณํํด์ค๋ค. ์ด์ ๋ค์ 012 ์ฌ์ฉ ๋ฐฉ๋ฒ git ์ฐธ๊ณ : https://github.com/crowsonkb/style-transfer-pytorch GitHub - crowsonkb/style-transfer-pytorch: Neural style transfer in PyTorch. Neural style transfer in PyTorch. Contribute to crowsonkb/style-transfer-pytorch development by creating an account on GitHub. github.com ๊ฐ์ํ๊ฒฝ ์ค์ ํ [ pip install -e . ] ์ค์น style_transfer_pytorch.egg-info ๊ฒฝ๋ก ์ค์ $ cd ~/code/deep_learning/style_transfer_pytorch.egg-info style_transfer main.jpg backgraound.jpg style_transfer CONTENT_IMAGE STYLE_IMAGE [STYLE_IMAGE ...] [-o OUTPUT_IMAGE] iterations: int = 500, 500๋ฒ ๋์์ ์์ํ ์ถ๋ ฅ(์กฐ์ ์ ๋ฐ๋ผ ํ๋ฆฌํฐ ์กฐ์ ํ๋ฆฌํฐ์ ์๊ฐ ๋น๋ก) ์กฐ๊ฑด์ด ํ์ํ ๋ฏ ํ๋ค. ์ฌ์ง ์ฉ๋์ ๋ํ ์ ํ ํ์ฅ์ ์ง์ ์๋ด Q. ์๋น์ค ํ๋ ค๋ฉด ์ด๋์ ๋ ์๊ฐ์ ๊ฒฐ๊ณผ๋ฌผ์ ๋ณด์ฌ์ค์ผ ํ๋์? - ๋ก๋ฉ์ด ๋๋ ์๊ฐ ๋์ ๋ค๋ฅธ ์์์ ํ์ด์ฃผ๋ ๋ฑ์ ์๋น์ค ์ ๊ณตํ๋๊ฒ ์ข์ ๋ฏ HOW? ์ด๋ป๊ฒ ์์ถ์ด ๋๋๊ฐ? ๋ณต์ ๊ณผ์ ์ ์ฌ๋ฌ๋ฒ์ ์ชผ๊ฐ๋ ๊ณผ์ ์ ํตํด ์ ์ฌํ ๋ ์ด์์์ ๊ตฌ๋ถํ๋ค. ๋ณต์ ๊ณผ์ ์์ ์คํ์ผ์ ์ ํ๋ค๊ณ ๋ณด๋ฉด ๋๋ค ๋ฅ๋ฌ๋ ๋ค๋ฅธ ์ข ๋ฅ ๋ฅํ์ดํฌ git : https://github.com/AliaksandrSiarohin/first-order-model GitHub - AliaksandrSiarohin/first-order-model: This repository contains the source code for the paper First Order Motion Model f This repository contains the source code for the paper First Order Motion Model for Image Animation - GitHub - AliaksandrSiarohin/first-order-model: This repository contains the source code for th... github.com SEFA git : https://github.com/genforce/sefa GitHub - genforce/sefa: [CVPR 2021] Closed-Form Factorization of Latent Semantics in GANs [CVPR 2021] Closed-Form Factorization of Latent Semantics in GANs - GitHub - genforce/sefa: [CVPR 2021] Closed-Form Factorization of Latent Semantics in GANs github.com ๋๋ณด๊ธฐ sefa-gan ์ฌ์ฉ๋ฐฉ๋ฒ 1. checkpoints ํด๋ ์์ ๋ชจ๋ธ ์ ์ฅ [๋ชจ๋ธ ๋ค์ด๋ก๋ ํ์ด์ง]https://github.com/genforce/genforce/blob/master/MODEL_ZOO.md [ํค์๋] car512, anime [๋ค์ด๋ก๋ํ ํ์ผ] stylegan_animeface512.pth 2.๋ชจ๋ธ ์ธํ MODEL_NAME=stylegan_animeface512LAYER_IDX=0-1NUM_SAMPLES=5NUM_SEMANTICS=5python sefa.py ${MODEL_NAME} \ -L ${LAYER_IDX} \ -N ${NUM_SAMPLES} \ -K ${NUM_SEMANTICS}3. pip install [streamlit ๋ฒ์ ์ถฉ๋์]pip uninstall streamlit[์ ์๋ฒ์ ]1. pip install streamlit==1.3.12. pip install opencv-python3. pip install torch==1.9.0+cu111 (๋ฒ์ ์ค๋ฅ) torchvision==0.10.0+cu111 torchaudio==0.9.0 -f https://download.pytorch.org/whl/torch_stable.html[์ด๊ฑธ๋ก ์งํ]pip install torch==1.9.0+cu111 torchvision==0.10.0+cu111 torchaudio==0.9.0 -f https://download.pytorch.org/whl/torch_stable.htmlpip install torch==1.11.0+cu115 -f https://download.pytorch.org/whl/torch_stable.htmlpip install torchvision==0.10.0+cu111 -f https://download.pytorch.org/whl/torch_stable.htmlpip install torchaudio==0.9.0 -f https://download.pytorch.org/whl/torch_stable.html4. ์คํCUDA_VISIBLE_DEVICES=0 streamlit run interface.py Simple StyleGan2 for Pytorch git : https://github.com/lucidrains/stylegan2-pytorch GitHub - lucidrains/stylegan2-pytorch: Simplest working implementation of Stylegan2, state of the art generative adversarial net Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement - GitHub - lucidrains/stylegan2-pytorch: S... github.com pix2pix git : https://github.com/phillipi/pix2pix GitHub - phillipi/pix2pix: Image-to-image translation with conditional adversarial nets Image-to-image translation with conditional adversarial nets - GitHub - phillipi/pix2pix: Image-to-image translation with conditional adversarial nets github.com ๊ณต์ ํ๊ธฐ URL ๋ณต์ฌ์นด์นด์คํก ๊ณต์ ํ์ด์ค๋ถ ๊ณต์ ์์ค ๊ณต์ ๊ฒ์๊ธ ๊ด๋ฆฌ ๊ตฌ๋ ํ๊ธฐMOVEMENT.DEV Contents ์ฌ์ฉ๋ฐฉ๋ฒ ๋ฅ๋ฌ๋๋ค๋ฅธ์ข ๋ฅ ๋ฅํ์ดํฌ SEFA sefa-gan์ฌ์ฉ๋ฐฉ๋ฒ SimpleStyleGan2forPytorch pix2pix ๋น์ ์ด ์ข์ํ ๋งํ ์ฝํ ์ธ TIL_220627_์ ํ ์ ์ ํ๋ก์ ํธ SA 2023.01.01 TIL_220630_rest_framework_simplejwt 2023.01.01 TIL_220621_DRF ๊ฐ์ 2023.01.01 TIL_220620_DRF ๊ฐ์ 2023.01.01 ๋๊ธ 0 + ์ด์ ๋๊ธ ๋๋ณด๊ธฐ