search

eric-ai-lab / photoswap

Official implementation of the NeurIPS 2023 paper "Photoswap: Personalized Subject Swapping in Images"
https://photoswap.github.io
MIT License
342 stars 24 forks source link

Version of torch when training the customized model #3

Closed ltl3A87 closed 1 year ago

ltl3A87 commented 1 year ago

Hi, thanks for the awesome work! May I know the torch version you used when training the two provided checkpoints? I tried to use the notebook to run photoswap, but got error when loading the model OSError: Unable to load weights from checkpoint file for 'checkpoints/justin-800/unet/diffusion_pytorch_model.bin' at 'checkpoints/justin-800/unet/diffusion_pytorch_model.bin'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.

g-jing commented 1 year ago

If you want to use the provided checkpoints, pytorch 1.13.1 should be enough. If you want to train your own checkpoint, you could follow the instruction here https://github.com/huggingface/diffusers/tree/main/examples/dreambooth

KabonMax commented 1 year ago

Thank you very much!

ChaeSeoyoung commented 2 months ago 
name: (envname)
channels:
  - pytorch
  - nvidia
  - conda-forge
  - defaults
dependencies:
  - asttokens=2.4.1=pyhd8ed1ab_0
  - blas=1.0=mkl
  - bottleneck=1.3.7=py39h9128911_0
  - brotli=1.0.9=h2bbff1b_7
  - brotli-bin=1.0.9=h2bbff1b_7
  - brotli-python=1.0.9=py39hd77b12b_7
  - ca-certificates=2024.7.4=h56e8100_0
  - certifi=2024.7.4=pyhd8ed1ab_0
  - charset-normalizer=2.0.4=pyhd3eb1b0_0
  - colorama=0.4.6=pyhd8ed1ab_0
  - comm=0.2.2=pyhd8ed1ab_0
  - contourpy=1.2.0=py39h59b6b97_0
  - cuda-cccl=12.4.99=0
  - cuda-cudart=11.7.99=0
  - cuda-cudart-dev=11.7.99=0
  - cuda-cupti=11.7.101=0
  - cuda-libraries=11.7.1=0
  - cuda-libraries-dev=11.7.1=0
  - cuda-nvrtc=11.7.99=0
  - cuda-nvrtc-dev=11.7.99=0
  - cuda-nvtx=11.7.91=0
  - cuda-runtime=11.7.1=0
  - cycler=0.11.0=pyhd3eb1b0_0
  - debugpy=1.8.1=py39h99910a6_0
  - decorator=5.1.1=pyhd8ed1ab_0
  - exceptiongroup=1.2.0=pyhd8ed1ab_2
  - executing=2.0.1=pyhd8ed1ab_0
  - filelock=3.13.1=py39haa95532_0
  - fonttools=4.25.0=pyhd3eb1b0_0
  - freetype=2.12.1=ha860e81_0
  - gmpy2=2.1.2=py39h7f96b67_0
  - icc_rt=2022.1.0=h6049295_2
  - icu=73.1=h6c2663c_0
  - idna=3.4=py39haa95532_0
  - importlib-metadata=7.1.0=pyha770c72_0
  - importlib_metadata=7.1.0=hd8ed1ab_0
  - importlib_resources=6.1.1=py39haa95532_1
  - intel-openmp=2023.1.0=h59b6b97_46320
  - ipykernel=6.29.3=pyha63f2e9_0
  - ipython=8.18.1=pyh7428d3b_3
  - ipywidgets=8.1.3=pyhd8ed1ab_0
  - jedi=0.19.1=pyhd8ed1ab_0
  - jinja2=3.1.3=py39haa95532_0
  - joblib=1.2.0=py39haa95532_0
  - jpeg=9e=h2bbff1b_1
  - jupyter_client=8.6.1=pyhd8ed1ab_0
  - jupyter_core=5.7.2=py39hcbf5309_0
  - jupyterlab_widgets=3.0.11=pyhd8ed1ab_0
  - kiwisolver=1.4.4=py39hd77b12b_0
  - krb5=1.20.1=h5b6d351_0
  - lerc=3.0=hd77b12b_0
  - libbrotlicommon=1.0.9=h2bbff1b_7
  - libbrotlidec=1.0.9=h2bbff1b_7
  - libbrotlienc=1.0.9=h2bbff1b_7
  - libclang=14.0.6=default_hb5a9fac_1
  - libclang13=14.0.6=default_h8e68704_1
  - libcublas=11.10.3.66=0
  - libcublas-dev=11.10.3.66=0
  - libcufft=10.7.2.124=0
  - libcufft-dev=10.7.2.124=0
  - libcurand=10.3.5.119=0
  - libcurand-dev=10.3.5.119=0
  - libcusolver=11.4.0.1=0
  - libcusolver-dev=11.4.0.1=0
  - libcusparse=11.7.4.91=0
  - libcusparse-dev=11.7.4.91=0
  - libdeflate=1.17=h2bbff1b_1
  - libnpp=11.7.4.75=0
  - libnpp-dev=11.7.4.75=0
  - libnvjpeg=11.8.0.2=0
  - libnvjpeg-dev=11.8.0.2=0
  - libpng=1.6.39=h8cc25b3_0
  - libpq=12.17=h906ac69_0
  - libsodium=1.0.18=h8d14728_1
  - libtiff=4.5.1=hd77b12b_0
  - libuv=1.44.2=h2bbff1b_0
  - libwebp-base=1.3.2=h2bbff1b_0
  - lz4-c=1.9.4=h2bbff1b_0
  - markupsafe=2.1.3=py39h2bbff1b_0
  - matplotlib=3.8.0=py39haa95532_0
  - matplotlib-base=3.8.0=py39h4ed8f06_0
  - matplotlib-inline=0.1.6=pyhd8ed1ab_0
  - mkl=2023.1.0=h6b88ed4_46358
  - mkl-service=2.4.0=py39h2bbff1b_1
  - mkl_fft=1.3.8=py39h2bbff1b_0
  - mkl_random=1.2.4=py39h59b6b97_0
  - mpc=1.1.0=h7edee0f_1
  - mpfr=4.0.2=h62dcd97_1
  - mpir=3.0.0=hec2e145_1
  - mpmath=1.3.0=py39haa95532_0
  - munkres=1.1.4=py_0
  - nest-asyncio=1.6.0=pyhd8ed1ab_0
  - networkx=3.1=py39haa95532_0
  - numexpr=2.8.7=py39h2cd9be0_0
  - numpy=1.26.4=py39h055cbcc_0
  - numpy-base=1.26.4=py39h65a83cf_0
  - openjpeg=2.4.0=h4fc8c34_0
  - openssl=3.3.1=h2466b09_2
  - packaging=24.0=pyhd8ed1ab_0
  - pandas=2.2.1=py39h5da7b33_0
  - parso=0.8.3=pyhd8ed1ab_0
  - pickleshare=0.7.5=py_1003
  - pillow=10.2.0=py39h2bbff1b_0
  - pip=23.3.1=py39haa95532_0
  - platformdirs=4.2.0=pyhd8ed1ab_0
  - ply=3.11=py39haa95532_0
  - prompt-toolkit=3.0.42=pyha770c72_0
  - psutil=5.9.8=py39ha55989b_0
  - pure_eval=0.2.2=pyhd8ed1ab_0
  - pygments=2.17.2=pyhd8ed1ab_0
  - pyparsing=3.0.9=py39haa95532_0
  - pyqt=5.15.10=py39hd77b12b_0
  - pyqt5-sip=12.13.0=py39h2bbff1b_0
  - pysocks=1.7.1=py39haa95532_0
  - python=3.9.19=h1aa4202_0
  - python-dateutil=2.9.0=pyhd8ed1ab_0
  - python-tzdata=2023.3=pyhd3eb1b0_0
  - python_abi=3.9=2_cp39
  - pytorch=2.0.0=py3.9_cuda11.7_cudnn8_0
  - pytorch-cuda=11.7=h16d0643_5
  - pytorch-mutex=1.0=cuda
  - pytz=2023.3.post1=py39haa95532_0
  - pywin32=306=py39h99910a6_2
  - pyzmq=25.1.2=py39h7eaf5a6_0
  - qt-main=5.15.2=h19c9488_10
  - requests=2.31.0=py39haa95532_1
  - scipy=1.12.0=py39h8640f81_0
  - setuptools=68.2.2=py39haa95532_0
  - sip=6.7.12=py39hd77b12b_0
  - six=1.16.0=pyh6c4a22f_0
  - sqlite=3.41.2=h2bbff1b_0
  - stack_data=0.6.2=pyhd8ed1ab_0
  - sympy=1.12=py39haa95532_0
  - tbb=2021.8.0=h59b6b97_0
  - threadpoolctl=2.2.0=pyh0d69192_0
  - tomli=2.0.1=py39haa95532_0
  - tornado=6.4=py39ha55989b_0
  - traitlets=5.14.2=pyhd8ed1ab_0
  - typing_extensions=4.9.0=py39haa95532_1
  - tzdata=2024a=h04d1e81_0
  - ucrt=10.0.22621.0=h57928b3_0
  - urllib3=2.1.0=py39haa95532_1
  - vc=14.2=h21ff451_1
  - vc14_runtime=14.38.33130=h82b7239_18
  - vs2015_runtime=14.38.33130=hcb4865c_18
  - wcwidth=0.2.13=pyhd8ed1ab_0
  - wheel=0.41.2=py39haa95532_0
  - widgetsnbextension=4.0.11=pyhd8ed1ab_0
  - win_inet_pton=1.1.0=py39haa95532_0
  - xz=5.4.6=h8cc25b3_0
  - zeromq=4.3.5=h63175ca_1
  - zipp=3.17.0=pyhd8ed1ab_0
  - zlib=1.2.13=h8cc25b3_0
  - zstd=1.5.5=hd43e919_0
  - pip:
      - appdirs==1.4.4
      - click==8.1.7
      - diffusers==0.14.0
      - docker-pycreds==0.4.0
      - dominate==2.9.1
      - einops==0.8.0
      - fsspec==2024.6.1
      - ftfy==6.2.3
      - gitdb==4.0.11
      - gitpython==3.1.43
      - huggingface-hub==0.24.6
      - jsonpatch==1.33
      - jsonpointer==2.4
      - opencv-python==4.10.0.84
      - protobuf==4.25.3
      - pyyaml==6.0.1
      - regex==2024.7.24
      - safetensors==0.4.4
      - scikit-learn==1.0.2
      - sentry-sdk==1.44.1
      - setproctitle==1.3.3
      - smmap==5.0.1
      - tokenizers==0.19.1
      - torchaudio==2.0.0
      - torchvision==0.15.0
      - tqdm==4.66.5
      - transformers==4.44.1
      - visdom==0.2.4
      - wandb==0.16.5
      - websocket-client==1.7.0
prefix: C:\Users\(username)\anaconda3\envs\(envname)

I succeed to run the code, and this is my exported .yaml file. I run it on windows, vscode. I hope it helps to make anaconda env.