search

zrqiao / NeuralPLexer

NeuralPLexer: State-specific protein-ligand complex structure prediction with a multi-scale deep generative model
https://doi.org/10.1038/s42256-024-00792-z
BSD 3-Clause Clear License
257 stars 68 forks source link

Make environment fails #1

Closed forcefield closed 7 months ago

forcefield commented 7 months ago

Description

I tried to build NeuralPlexer, but failed at building the environment. It seems that openfold is anticipating a different compiler version.

     /usr/local/cuda/bin/nvcc -I/tmp/pip-install-cha4n9yk/openfold_11bccc4449554c609bc856dc695361f0/openfold/utils/kernel/csrc/ -I/path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include -I/path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/torch/csrc/api/include -I/path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/TH -I/path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/THC -I/usr/local/cuda/include -I/path/to/conda/envs/neuralplexer_dev/include/python3.10 -c openfold/utils/kernel/csrc/softmax_cuda_kernel.cu -o build/temp.linux-x86_64-cpython-310/openfold/utils/kernel/csrc/softmax_cuda_kernel.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -O3 --use_fast_math -DVERSION_GE_1_1 -DVERSION_GE_1_3 -DVERSION_GE_1_5 -std=c++14 -maxrregcount=50 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ --expt-relaxed-constexpr --expt-extended-lambda -gencode arch=compute_89,code=sm_89 -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=attn_core_inplace_cuda -D_GLIBCXX_USE_CXX11_ABI=0
      In file included from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/torch/extension.h:5,
                       from openfold/utils/kernel/csrc/softmax_cuda_kernel.cu:18:
      /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/all.h:4:2: error: #error C++17 or later compatible compiler is required to use PyTorch.
          4 | #error C++17 or later compatible compiler is required to use PyTorch.
            |  ^~~~~
      In file included from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/c10/util/string_view.h:4,
                       from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/c10/util/StringUtil.h:6,
                       from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/c10/util/Exception.h:5,
                       from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/c10/core/Device.h:5,
                       from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/ATen/core/TensorBody.h:11,
                       from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/ATen/core/Tensor.h:3,
                       from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/ATen/Tensor.h:3,
                       from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/torch/csrc/autograd/function_hook.h:3,
                       from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/torch/csrc/autograd/cpp_hook.h:2,
                       from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/torch/csrc/autograd/variable.h:6,
                       from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/torch/csrc/autograd/autograd.h:3,
                       from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/autograd.h:3,
                       from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/all.h:7,
                       from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/torch/extension.h:5,
                       from openfold/utils/kernel/csrc/softmax_cuda_kernel.cu:18:
      /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/c10/util/C++17.h:27:2: error: #error You need C++17 to compile PyTorch
         27 | #error You need C++17 to compile PyTorch
            |  ^~~~~
      In file included from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                       from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                       from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                       from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:4,
                       from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                       from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                       from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/all.h:9,
                       from /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/torch/extension.h:5,
                       from openfold/utils/kernel/csrc/softmax_cuda_kernel.cu:18:
      /path/to/conda/envs/neuralplexer_dev/lib/python3.10/site-packages/torch/include/ATen/ATen.h:4:2: error: #error C++17 or later compatible compiler is required to use ATen.
          4 | #error C++17 or later compatible compiler is required to use ATen.
            |  ^~~~~
      error: command '/usr/local/cuda/bin/nvcc' failed with exit code 1
      [end of output]

  note: This error originates from a subprocess, and is likely not a problem with pip.
  ERROR: Failed building wheel for openfold
ERROR: Could not build wheels for openfold, which is required to install pyproject.toml-based projects

failed

CondaEnvException: Pip failed

make: *** [Makefile:87: environment] Error 1

What I Did

make environment
MKCarter commented 7 months ago

This is because you need to pin certain versions of torch, torchvision and torch-scatter - otherwise openfold will not install and torch will error. If you set: In the env yml -

pytorch=1.11.0

In the requirements txt:

torch-scatter==2.0.9
torchvision==1.12.0

You will be able to install without any problems.

I hope this helps.

MKCarter commented 7 months ago

So... this didn't work, but updating the yml and requirements.txt did indeed work:

For the yaml:

name: neuralplexer_dev
channels:
  - nvidia
  - pytorch
  - pytorch3d
  - pyg
  - bioconda
  - conda-forge
dependencies:
  - python=3.9
  - pip
  - pytorch=1.13.1
  - pytorch-cuda
  - biopython
  - prody
  - deprecated
  - hydra-core=1.1.1
  - dm-tree
  - ml-collections
  - networkx
  - pypdb
  - pytest
  - dataclasses
  - msgpack-python
  - msgpack-numpy
  - numpy
  - openbabel
  - pandas
  - pytorch3d
  - rdkit
  - rmsd
  - tmalign
  - tensorboard
  - jupyter
  - tqdm
  - python-lmdb
  - vim
  - wandb
  - pip:
    - -r requirements.txt

And for the requirements.txt:

pytorch-lightning <2.0.0
torch-scatter==2.1.0
torchvision==0.14.1
fairscale
mendeleev
DLLogger @ git+https://github.com/NVIDIA/dllogger.git@0540a43971f4a8a16693a9de9de73c1072020769
openfold @ git+https://github.com/aqlaboratory/openfold.git@103d0370ad9ce07579c20fa9c889a632f9b16618
power-spherical @ git+https://git@github.com/zrqiao/power_spherical.git@290b1630c5f84e3bb0d61711046edcf6e47200d4
fair-esm @ git+https://github.com/facebookresearch/esm@57da016e5d740a9ac5bcf62c3689a42e88584bc
seaborn

This will give you a working env that can run both the inference and training.

Again, I hope this helps!

forcefield commented 7 months ago

It now complains that 

RuntimeError:
      The detected CUDA version (12.0) mismatches the version that was used to compile
      PyTorch (11.7). Please make sure to use the same CUDA versions.

Does this install work with CUDA 12? Thanks!

MKCarter commented 7 months ago

I see - this is likely an issue with the cudatoolkit version in your env and your nvcc version - for me I am using:

cudatoolkit 11.8.0 h4ba93d1_13 conda-forge

Within this environment. If I check my nvcc version:

nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2022 NVIDIA Corporation
Built on Wed_Sep_21_10:33:58_PDT_2022
Cuda compilation tools, release 11.8, V11.8.89
Build cuda_11.8.r11.8/compiler.31833905_0

I can see that this matched. So I know It works using 11.8 - that is all I can say.

Maybe try downgrading your nvcc to a lower version, or ensuring that your cudatoolkit version matches your nvcc that you have installed.

RMichae1 commented 7 months ago

Hello, @forcefield I did experience the same initial error. You can resolve the building of openfold by setting the build flags in the setup.py (of openfold) to std=c++17, it is per default set to 14, which breaks CUDA11.8 compilation. Also make sure the loaded gcc version is less than 11 . My default was 13.3 and loading gcc/10.2.0 did the trick with the correct flag.

The secondary issue with mismatch in PyTorch CUDA compiled version I've mitigated by manually installing the correct CUDA (for me cu118) prior to doing the pip installs.

Hope that helps. Cheers

EDIT: Curiously the installation resolves, but running the inference CLI I get the following import error:

ImportError: /path/to/home/.conda/envs/neuralplexer_dev/lib/python3.10/site-packages/pytorch3d/_C.cpython-310-x86_64-linux-gnu.so: undefined symbol: _ZN2at4_ops10zeros_like4callERKNS_6TensorEN3c108optionalINS5_10ScalarTypeEEENS6_INS5_6LayoutEEENS6_INS5_6DeviceEEENS6_IbEENS6_INS5_12MemoryFormatEEE

which is not resolved by installing pytorch3d as described here.

EDIT2: After installation is resolved and if there is a mismatch in CUDA/Torch compatibility specific to pytorch3d try reinstalling the pytorch3d installation from source: pip install "git+https://github.com/facebookresearch/pytorch3d.git@stable" . Conda/Mamba might fail to resolve for the correct torch/CUDA binaries .

RMichae1 commented 7 months ago

To follow up appropriately:

PIGT: Python version: 3.10.13 Linux: RedHat EL, Fedora 8.9 ; 4.18.0-513.5.1.el8_9.x86_64 NVIDIA-SMI 545.23.08 Driver Version: 545.23.08 CUDA Version: 12.3 final installed version for all GPU units CUDA=11.8

  1. Initial mamba env create -f environment_dev.yaml failed due to openfold installation error, initially mismatch in CUDA versions 12.1 (PyTorch) vs 11.8 (installed)
  2. manual installation of PyTorch for cu118: pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118 fixed the mismatch
  3. openfold installation still failing due to #error C++17 as indicated by @forcefield
  4. downgrade of local gcc required to version lower than 11.0.0 , manual change of setup.py set extra_cuda_flags to std=c++17 -- this successfully installs openfold
  5. manually install all listed pip packages remaining after conda errors, this should resolve now
  6. run make install to finish installation
  7. on testing the neuralplexer-inference CLI the run fails due to pytorch3d failing on import : _C.cpython-310-x86_64-linux-gnu.so: undefined symbol: _ZN2at4_ops10zeros_like4callERKNS_6TensorEN3c108optionalINS5_10ScalarTypeEEENS6_INS5_6LayoutEEENS6_INS5_6DeviceEEENS6_IbEENS6_INS5_12MemoryFormatEEE this indicates a mismatch between the (mamba/conda) installed pytorch3d and the current torch/CUDA versions
  8. following pytorch3d repository installation instructions required building from source via pip install, --force-reinstall --no-deps, since otherwise other version conflicts will be created by pytorch3d installation

After unpacking the model checkpoints the neuralplexer-inference CLI should work correctly now.

forcefield commented 7 months ago

@RMichae1 Thanks for tracing this!

How do you install PyTorch for cu118 in the same conda environment that step 1 is trying to create unsuccessfully?

In step 4, do you mean that you need to do a standard alone installation of openfold? Likewise for step 8, do you build pytorch3d in the same conda environment that step 1 is trying create?

tkram01 commented 7 months ago

Here is a Dockerfile that is working for me Dockerfile NeuralPLexer-requirements.txt NeuralPLexer.yml

RMichae1 commented 7 months ago

@RMichae1 Thanks for tracing this!

How do you install PyTorch for cu118 in the same conda environment that step 1 is trying to create unsuccessfully?

In step 4, do you mean that you need to do a standard alone installation of openfold? Likewise for step 8, do you build pytorch3d in the same conda environment that step 1 is trying create?

@forcefield If resolving the environment with conda (or mamba) fails on the pip (requirements) installs, an environment should have already been created at this point. So you should be able to activate the neuralplexer_dev environment and work from there. You should be able to install PyTorch cu118 there (within the neuralplexer_dev environment).

Re step 4: There are different ways to resolve this. You can check-out (/clone) openfold at the pinned commit id and modify the setup.py . I cloned openfold directly (not at the pinned commit), modified the setup file and ran pip install -e . (where . refers to the openfold directory) - the pip install is required to be run in the neuralplexer_dev environment. And lastly the pytorch3d has to be installed in the same conda environment - the neuralplexer_dev environment via the appropriate pip install. This should be a pip install --force-reinstall --no-deps "git+https://github.com/facebookresearch/pytorch3d.git@stable" the reinstall is required, since a pytorch3d installation should have been present due to the initial conda/mamba resolve and the no-deps flag is required as to not reinstall pytorch and other dependencies.

Hope that helps! Cheers

PS: I'm only doing this because Docker is not an option on the target HPC system.

forcefield commented 7 months ago

Thanks a lot! This worked with just one small change to the Dockerfile:

Best, Huafeng

On Sat, Feb 17, 2024 at 8:04 AM tkram01 @.***> wrote:

Here is a Dockerfile that is working for me Dockerfile https://github.com/zrqiao/NeuralPLexer/files/14318848/Dockerfile-NeuralPLexer.txt NeuralPLexer-requirements.txt https://github.com/zrqiao/NeuralPLexer/files/14318846/NeuralPLexer-requirements.txt NeuralPLexer.yml https://github.com/zrqiao/NeuralPLexer/files/14318852/NeuralPLexer_yml.txt

— Reply to this email directly, view it on GitHub https://github.com/zrqiao/NeuralPLexer/issues/1#issuecomment-1950118696, or unsubscribe https://github.com/notifications/unsubscribe-auth/AADU52CB72LLXHJPVJ2MGLTYUCTG3AVCNFSM6AAAAABDGX7KQOVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTSNJQGEYTQNRZGY . You are receiving this because you were mentioned.Message ID: @.***>

forcefield commented 7 months ago

Here is the full Dockerfile that worked for me. Thanks to @tkram01 for the enabling hard work and sharing.

FROM nvidia/cuda:11.7.1-devel-ubuntu22.04

RUN apt-get update \
    && DEBIAN_FRONTEND=noninteractive apt-get install --no-install-recommends -y \
        make \
        git \
        wget \
        tzdata \
        awscli \
    && rm -rf /var/lib/apt/lists/* \
    && apt-get autoremove -y \
    && apt-get clean

SHELL ["/bin/bash", "--login", "-c"]

ENV CONDA_DIR /opt/conda
RUN wget --quiet https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda.sh && \
    /bin/bash ~/miniconda.sh -b -p /opt/conda && rm ~/miniconda.sh
ENV PATH=$CONDA_DIR/bin:$PATH

RUN conda init bash

RUN conda create -n NeuralPLexer python=3.9

RUN echo "conda activate NeuralPLexer" >> ~/.bashrc

RUN conda run -n NeuralPLexer pip install torch==1.13.1+cu117 torchvision==0.14.1+cu117 torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cu117 --no-cache-dir
RUN conda run -n NeuralPLexer pip install torch-scatter==2.1.0 -f https://data.pyg.org/whl/torch-1.13.1+cu117.html --no-cache-dir
RUN conda run -n NeuralPLexer pip install "git+https://github.com/facebookresearch/pytorch3d.git" --force-reinstall --no-deps --no-cache-dir

RUN git clone https://github.com/aqlaboratory/openfold.git
RUN cd openfold && sed -i 's/std=c++14/std=c++17/g' setup.py && conda run -n NeuralPLexer pip install . && cd ../ && rm -rf openfold

COPY NeuralPLexer.yml .
COPY NeuralPLexer-requirements.txt .
RUN conda run -n NeuralPLexer conda env update --file NeuralPLexer.yml && conda run -n NeuralPLexer conda clean -afy

RUN git clone https://github.com/zrqiao/NeuralPLexer.git && cd NeuralPLexer && conda run -n NeuralPLexer make install

ENTRYPOINT ["conda", "run", "-n", "NeuralPLexer"]
zrqiao commented 7 months ago

Thanks so much for the contributions @tkram01 , @forcefield , @MKCarter , and @RMichae1 ! Hey @forcefield , would you be willing to make a PR to enable a docker build of the package? In due time, I will update the main branch with (1) better version pins for the dependencies and (2) removal of warnings that do not affect model prediction.

forcefield commented 7 months ago

Glad to help! Please add me to the repository so that I can contribute to it. Thanks!

On Tue, Feb 20, 2024 at 3:25 PM Zhuoran Qiao @.***> wrote:

Thanks so much for the contributions @tkram01 https://github.com/tkram01 , @forcefield https://github.com/forcefield , @MKCarter https://github.com/MKCarter , and @RMichae1 https://github.com/RMichae1 ! Hey @forcefield https://github.com/forcefield , would you be willing to make a PR to enable a docker build of the package? In due time, I will update the main branch with (1) better version pins for the dependencies and (2) removal of warnings that do not affect model prediction.

— Reply to this email directly, view it on GitHub https://github.com/zrqiao/NeuralPLexer/issues/1#issuecomment-1955012286, or unsubscribe https://github.com/notifications/unsubscribe-auth/AADU52GUXN5RZWBCVX5DITLYUUBFLAVCNFSM6AAAAABDGX7KQOVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTSNJVGAYTEMRYGY . You are receiving this because you were mentioned.Message ID: @.***>

zrqiao commented 7 months ago

Glad to help! Please add me to the repository so that I can contribute to it. Thanks! … On Tue, Feb 20, 2024 at 3:25 PM Zhuoran Qiao @.> wrote: Thanks so much for the contributions @tkram01 https://github.com/tkram01 , @forcefield https://github.com/forcefield , @MKCarter https://github.com/MKCarter , and @RMichae1 https://github.com/RMichae1 ! Hey @forcefield https://github.com/forcefield , would you be willing to make a PR to enable a docker build of the package? In due time, I will update the main branch with (1) better version pins for the dependencies and (2) removal of warnings that do not affect model prediction. — Reply to this email directly, view it on GitHub <#1 (comment)>, or unsubscribe https://github.com/notifications/unsubscribe-auth/AADU52GUXN5RZWBCVX5DITLYUUBFLAVCNFSM6AAAAABDGX7KQOVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTSNJVGAYTEMRYGY . You are receiving this because you were mentioned.Message ID: @.>

Thanks @forcefield ! I have added you to the repo contributors. In general, for any public repo you could also create a fork with requested changes and make a pull request to the upstream repo.

John-zzh commented 6 months ago

Here is the full Dockerfile that worked for me. Thanks to @tkram01 for the enabling hard work and sharing.

FROM nvidia/cuda:11.7.1-devel-ubuntu22.04

RUN apt-get update \
   && DEBIAN_FRONTEND=noninteractive apt-get install --no-install-recommends -y \
       make \
       git \
       wget \
       tzdata \
       awscli \
   && rm -rf /var/lib/apt/lists/* \
   && apt-get autoremove -y \
   && apt-get clean

SHELL ["/bin/bash", "--login", "-c"]

ENV CONDA_DIR /opt/conda
RUN wget --quiet https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda.sh && \
   /bin/bash ~/miniconda.sh -b -p /opt/conda && rm ~/miniconda.sh
ENV PATH=$CONDA_DIR/bin:$PATH

RUN conda init bash

RUN conda create -n NeuralPLexer python=3.9

RUN echo "conda activate NeuralPLexer" >> ~/.bashrc

RUN conda run -n NeuralPLexer pip install torch==1.13.1+cu117 torchvision==0.14.1+cu117 torchaudio==0.13.1 --extra-index-url https://download.pytorch.org/whl/cu117 --no-cache-dir
RUN conda run -n NeuralPLexer pip install torch-scatter==2.1.0 -f https://data.pyg.org/whl/torch-1.13.1+cu117.html --no-cache-dir
RUN conda run -n NeuralPLexer pip install "git+https://github.com/facebookresearch/pytorch3d.git" --force-reinstall --no-deps --no-cache-dir

RUN git clone https://github.com/aqlaboratory/openfold.git
RUN cd openfold && sed -i 's/std=c++14/std=c++17/g' setup.py && conda run -n NeuralPLexer pip install . && cd ../ && rm -rf openfold

COPY NeuralPLexer.yml .
COPY NeuralPLexer-requirements.txt .
RUN conda run -n NeuralPLexer conda env update --file NeuralPLexer.yml && conda run -n NeuralPLexer conda clean -afy

RUN git clone https://github.com/zrqiao/NeuralPLexer.git && cd NeuralPLexer && conda run -n NeuralPLexer make install

ENTRYPOINT ["conda", "run", "-n", "NeuralPLexer"]

Hi forcefield, What's the CUDA and gcc version in your setup? I used CUDA 11.7 and gcc 10.5 and follow your steps solely using conda and pip (not docker), and after pip install the openfold (pip install .), it does not pass the test by runig "scripts/run_unit_tests.sh" in the openfold dir. I assume it has to correctly install openfold before install neuralplexer? But openfold repo needs CUDA11.3 and pytorch 1.12.1, etc. I'm so confused here :-(

danid77 commented 1 month ago

DLLogger @ git+https://github.com/NVIDIA/dllogger.git@0540a43971f4a8a16693a9de9de73c1072020769 openfold @ git+https://github.com/aqlaboratory/openfold.git@103d0370ad9ce07579c20fa9c889a632f9b16618 power-spherical @ git+https://git@github.com/zrqiao/power_spherical.git@290b1630c5f84e3bb0d61711046edcf6e47200d4 fair-esm @ git+https://github.com/facebookresearch/esm@57da016e5d740a9ac5bcf62c3689a42e88584bc

I think this version is no longer available. Is there a workaround?

MKCarter commented 1 month ago

As far as I can see - it looks like this should still work - if you have torch installed you should be able to run the following:

pip install DLLogger@git+https://github.com/NVIDIA/dllogger.git@0540a43971f4a8a16693a9de9de73c1072020769
pip install openfold@git+https://github.com/aqlaboratory/openfold.git@103d0370ad9ce07579c20fa9c889a632f9b16618
pip install power-spherical@git+https://git@github.com/zrqiao/power_spherical.git@290b1630c5f84e3bb0d61711046edcf6e47200d4
pip install fair-esm@git+https://github.com/facebookresearch/esm@57da016e5d740a9ac5bcf62c3689a42e88584bc

I just ran this in a fresh environment and this is the output I have:

Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Collecting DLLogger@ git+https://github.com/NVIDIA/dllogger.git@0540a43971f4a8a16693a9de9de73c1072020769
  Cloning https://github.com/NVIDIA/dllogger.git (to revision 0540a43971f4a8a16693a9de9de73c1072020769) to /tmp/pip-install-xf9mi5rw/dllogger_86b15378365c4c788894dd3cb6c9bc58
  Running command git clone --filter=blob:none --quiet https://github.com/NVIDIA/dllogger.git /tmp/pip-install-xf9mi5rw/dllogger_86b15378365c4c788894dd3cb6c9bc58
  Running command git rev-parse -q --verify 'sha^0540a43971f4a8a16693a9de9de73c1072020769'
  Running command git fetch -q https://github.com/NVIDIA/dllogger.git 0540a43971f4a8a16693a9de9de73c1072020769
  Resolved https://github.com/NVIDIA/dllogger.git to commit 0540a43971f4a8a16693a9de9de73c1072020769
  Preparing metadata (setup.py) ... done
Building wheels for collected packages: DLLogger
  Building wheel for DLLogger (setup.py) ... done
  Created wheel for DLLogger: filename=DLLogger-1.0.0-py3-none-any.whl size=5654 sha256=f54a1a65a4f5f2778c1e3977a9bdd9e11bc10803265ce4752515bd5b691dccfe
  Stored in directory: /tmp/pip-ephem-wheel-cache-i_z8zgqo/wheels/e9/8d/3f/d9eb545644ec998a186f0ae00a851d4e5467369830f5877d53
Successfully built DLLogger
Installing collected packages: DLLogger
Successfully installed DLLogger-1.0.0
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Collecting openfold@ git+https://github.com/aqlaboratory/openfold.git@103d0370ad9ce07579c20fa9c889a632f9b16618
  Cloning https://github.com/aqlaboratory/openfold.git (to revision 103d0370ad9ce07579c20fa9c889a632f9b16618) to /tmp/pip-install-veynr890/openfold_2c132d795351463fa9a42a21a60d2e72
  Running command git clone --filter=blob:none --quiet https://github.com/aqlaboratory/openfold.git /tmp/pip-install-veynr890/openfold_2c132d795351463fa9a42a21a60d2e72
  Running command git rev-parse -q --verify 'sha^103d0370ad9ce07579c20fa9c889a632f9b16618'
  Running command git fetch -q https://github.com/aqlaboratory/openfold.git 103d0370ad9ce07579c20fa9c889a632f9b16618
  Running command git checkout -q 103d0370ad9ce07579c20fa9c889a632f9b16618
  Resolved https://github.com/aqlaboratory/openfold.git to commit 103d0370ad9ce07579c20fa9c889a632f9b16618
  Preparing metadata (setup.py) ... done
Building wheels for collected packages: openfold
  Building wheel for openfold (setup.py) ... done
  Created wheel for openfold: filename=openfold-1.0.1-cp39-cp39-linux_x86_64.whl size=285116 sha256=9481eecd20405355f6c29e57319126ec1f4ab9785199a65334d1ce58968bbd82
  Stored in directory: /tmp/pip-ephem-wheel-cache-_5lr9yzh/wheels/bb/fa/65/c6478011890e2ef41a8d7c8b0b3739509564da278e00345c39
Successfully built openfold
Installing collected packages: openfold
Successfully installed openfold-1.0.1
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Collecting power-spherical@ git+https://****@github.com/zrqiao/power_spherical.git@290b1630c5f84e3bb0d61711046edcf6e47200d4
  Cloning https://****@github.com/zrqiao/power_spherical.git (to revision 290b1630c5f84e3bb0d61711046edcf6e47200d4) to /tmp/pip-install-358wr2e6/power-spherical_beb4f68d83184db899d400641da31dd2
  Running command git clone --filter=blob:none --quiet 'https://****@github.com/zrqiao/power_spherical.git' /tmp/pip-install-358wr2e6/power-spherical_beb4f68d83184db899d400641da31dd2
  Running command git rev-parse -q --verify 'sha^290b1630c5f84e3bb0d61711046edcf6e47200d4'
  Running command git fetch -q 'https://****@github.com/zrqiao/power_spherical.git' 290b1630c5f84e3bb0d61711046edcf6e47200d4
  Resolved https://****@github.com/zrqiao/power_spherical.git to commit 290b1630c5f84e3bb0d61711046edcf6e47200d4
  Preparing metadata (setup.py) ... done
Requirement already satisfied: torch>=1.5.0 in ./miniconda3/envs/test_pip/lib/python3.9/site-packages (from power-spherical@ git+https://git@github.com/zrqiao/power_spherical.git@290b1630c5f84e3bb0d61711046edcf6e47200d4) (1.13.1)
Requirement already satisfied: typing-extensions in ./miniconda3/envs/test_pip/lib/python3.9/site-packages (from torch>=1.5.0->power-spherical@ git+https://git@github.com/zrqiao/power_spherical.git@290b1630c5f84e3bb0d61711046edcf6e47200d4) (4.12.2)
Requirement already satisfied: nvidia-cuda-runtime-cu11==11.7.99 in ./miniconda3/envs/test_pip/lib/python3.9/site-packages (from torch>=1.5.0->power-spherical@ git+https://git@github.com/zrqiao/power_spherical.git@290b1630c5f84e3bb0d61711046edcf6e47200d4) (11.7.99)
Requirement already satisfied: nvidia-cudnn-cu11==8.5.0.96 in ./miniconda3/envs/test_pip/lib/python3.9/site-packages (from torch>=1.5.0->power-spherical@ git+https://git@github.com/zrqiao/power_spherical.git@290b1630c5f84e3bb0d61711046edcf6e47200d4) (8.5.0.96)
Requirement already satisfied: nvidia-cublas-cu11==11.10.3.66 in ./miniconda3/envs/test_pip/lib/python3.9/site-packages (from torch>=1.5.0->power-spherical@ git+https://git@github.com/zrqiao/power_spherical.git@290b1630c5f84e3bb0d61711046edcf6e47200d4) (11.10.3.66)
Requirement already satisfied: nvidia-cuda-nvrtc-cu11==11.7.99 in ./miniconda3/envs/test_pip/lib/python3.9/site-packages (from torch>=1.5.0->power-spherical@ git+https://git@github.com/zrqiao/power_spherical.git@290b1630c5f84e3bb0d61711046edcf6e47200d4) (11.7.99)
Requirement already satisfied: setuptools in ./miniconda3/envs/test_pip/lib/python3.9/site-packages (from nvidia-cublas-cu11==11.10.3.66->torch>=1.5.0->power-spherical@ git+https://git@github.com/zrqiao/power_spherical.git@290b1630c5f84e3bb0d61711046edcf6e47200d4) (72.1.0)
Requirement already satisfied: wheel in ./miniconda3/envs/test_pip/lib/python3.9/site-packages (from nvidia-cublas-cu11==11.10.3.66->torch>=1.5.0->power-spherical@ git+https://git@github.com/zrqiao/power_spherical.git@290b1630c5f84e3bb0d61711046edcf6e47200d4) (0.44.0)
Building wheels for collected packages: power-spherical
  Building wheel for power-spherical (setup.py) ... done
  Created wheel for power-spherical: filename=power_spherical-0.1.0-py3-none-any.whl size=5276 sha256=39defc370b3f3ff8d4a26ed5a7a6f57a3f5baf39efb4b904e05aafa3f22248a0
  Stored in directory: /tmp/pip-ephem-wheel-cache-dga1thdw/wheels/48/46/63/29262300fd5b96ce075cdd847d0a4c70131f6cb49233589658
Successfully built power-spherical
Installing collected packages: power-spherical
Successfully installed power-spherical-0.1.0
Looking in indexes: https://pypi.org/simple, https://pypi.ngc.nvidia.com
Collecting fair-esm@ git+https://github.com/facebookresearch/esm@57da016e5d740a9ac5bcf62c3689a42e88584bc
  Cloning https://github.com/facebookresearch/esm (to revision 57da016e5d740a9ac5bcf62c3689a42e88584bc) to /tmp/pip-install-05c9cas6/fair-esm_7a5fa60e14034b7d8e388ecc026ec992
  Running command git clone --filter=blob:none --quiet https://github.com/facebookresearch/esm /tmp/pip-install-05c9cas6/fair-esm_7a5fa60e14034b7d8e388ecc026ec992
  WARNING: Did not find branch or tag '57da016e5d740a9ac5bcf62c3689a42e88584bc', assuming revision or ref.
  Running command git checkout -q 57da016e5d740a9ac5bcf62c3689a42e88584bc
  Resolved https://github.com/facebookresearch/esm to commit 57da016e5d740a9ac5bcf62c3689a42e88584bc
  Installing build dependencies ... done
  Getting requirements to build wheel ... done
  Preparing metadata (pyproject.toml) ... done
Building wheels for collected packages: fair-esm
  Building wheel for fair-esm (pyproject.toml) ... done
  Created wheel for fair-esm: filename=fair_esm-2.0.1-py3-none-any.whl size=95474 sha256=d1a55a9436ad6cc93646c7ffeb67459459f282b7d5ef0db55a12b320c97b51fe
  Stored in directory: /tmp/pip-ephem-wheel-cache-my5hbyl9/wheels/eb/71/85/15806313aef887b7cff981e191e63e585c7ad93d24554e084a
Successfully built fair-esm
Installing collected packages: fair-esm
Successfully installed fair-esm-2.0.1

It does appear that for fair-esm the branch or tag may have changed, but it should still install fair-esm for you. Could you post the error you are seeing? Thanks, Mike

danid77 commented 1 month ago

Preparing metadata (setup.py): started Preparing metadata (setup.py): finished with status 'error'

Pip subprocess error: Running command git clone --filter=blob:none --quiet https://github.com/NVIDIA/dllogger.git /tmp/pip-install-cxr8vymu/dllogger_d657669e7bc84a7fba24d02e5237d21f Running command git rev-parse -q --verify 'sha^0540a43971f4a8a16693a9de9de73c1072020769' Running command git fetch -q https://github.com/NVIDIA/dllogger.git 0540a43971f4a8a16693a9de9de73c1072020769 Running command git clone --filter=blob:none --quiet https://github.com/aqlaboratory/openfold.git /tmp/pip-install-cxr8vymu/openfold_0b5d96e1c866436e94c1ad1ca93495a2 Running command git rev-parse -q --verify 'sha^103d0370ad9ce07579c20fa9c889a632f9b16618' Running command git fetch -q https://github.com/aqlaboratory/openfold.git 103d0370ad9ce07579c20fa9c889a632f9b16618 Running command git checkout -q 103d0370ad9ce07579c20fa9c889a632f9b16618 error: subprocess-exited-with-error

× python setup.py egg_info did not run successfully. │ exit code: 1 ╰─> [8 lines of output] Traceback (most recent call last): File "", line 2, in File "", line 34, in File "/tmp/pip-install-cxr8vymu/openfold_0b5d96e1c866436e94c1ad1ca93495a2/setup.py", line 19, in import torch File "/home/lnptest/anaconda3/envs/neuralplexer_dev/lib/python3.9/site-packages/torch/init.py", line 218, in from torch._C import * # noqa: F403 ImportError: /home/lnptest/anaconda3/envs/neuralplexer_dev/lib/python3.9/site-packages/torch/lib/libtorch_cpu.so: undefined symbol: iJIT_NotifyEvent [end of output]

note: This error originates from a subprocess, and is likely not a problem with pip. error: metadata-generation-failed

× Encountered error while generating package metadata. ╰─> See above for output.

note: This is an issue with the package mentioned above, not pip. hint: See above for details. failed

CondaEnvException: Pip failed

The following error occurs, and I can't proceed any further. Everything else works fine, but I keep encountering errors when trying to install OpenFold.

Thanks, Danid

MKCarter commented 1 month ago

Hi Danid,

It looks like this is due to the version of torch you have installed - this line is the key to the error:

ImportError: /home/lnptest/anaconda3/envs/neuralplexer_dev/lib/python3.9/site-packages/torch/lib/libtorch_cpu.so: undefined symbol: iJIT_NotifyEvent

Did you install torch without cuda? Do you have a GPU enabled machine?

I think to install and run NeuralPlexer cuda enabled torch is needed.

danid77 commented 1 month ago

nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2022 NVIDIA Corporation Built on Tue_May__3_18:49:52_PDT_2022 Cuda compilation tools, release 11.7, V11.7.64 Build cuda_11.7.r11.7/compiler.31294372_0

I had installed version 11.7 of CUDA. However, I keep encountering errors.

Thanks, Danid

MKCarter commented 1 month ago

And if you run conda listin your environment do you see something similar to this:

conda list
# packages in environment at /home/michaelcarter/miniconda3/envs/neuralplexer_dev:
#
# Name                    Version                   Build  Channel
_libgcc_mutex             0.1                 conda_forge    conda-forge
_openmp_mutex             4.5                  2_kmp_llvm    conda-forge
absl-py                   2.1.0              pyhd8ed1ab_0    conda-forge
aiohttp                   3.9.3            py39hd1e30aa_0    conda-forge
aiosignal                 1.3.1              pyhd8ed1ab_0    conda-forge
antlr-python-runtime      4.8              py39hde42818_2    conda-forge
anyio                     4.2.0              pyhd8ed1ab_0    conda-forge
appdirs                   1.4.4              pyh9f0ad1d_0    conda-forge
argon2-cffi               23.1.0             pyhd8ed1ab_0    conda-forge
argon2-cffi-bindings      21.2.0           py39hd1e30aa_4    conda-forge
arrow                     1.3.0              pyhd8ed1ab_0    conda-forge
asttokens                 2.4.1              pyhd8ed1ab_0    conda-forge
async-lru                 2.0.4              pyhd8ed1ab_0    conda-forge
async-timeout             4.0.3              pyhd8ed1ab_0    conda-forge
attrs                     23.2.0             pyh71513ae_0    conda-forge
babel                     2.14.0             pyhd8ed1ab_0    conda-forge
beautifulsoup4            4.12.3             pyha770c72_0    conda-forge
biopython                 1.83             py39hd1e30aa_0    conda-forge
blas                      2.121                       mkl    conda-forge
blas-devel                3.9.0            21_linux64_mkl    conda-forge
bleach                    6.1.0              pyhd8ed1ab_0    conda-forge
blinker                   1.7.0              pyhd8ed1ab_0    conda-forge
brotli                    1.1.0                hd590300_1    conda-forge
brotli-bin                1.1.0                hd590300_1    conda-forge
brotli-python             1.1.0            py39h3d6467e_1    conda-forge
bzip2                     1.0.8                hd590300_5    conda-forge
c-ares                    1.26.0               hd590300_0    conda-forge
ca-certificates           2024.2.2             hbcca054_0    conda-forge
cached-property           1.5.2                hd8ed1ab_1    conda-forge
cached_property           1.5.2              pyha770c72_1    conda-forge
cachetools                5.3.2              pyhd8ed1ab_0    conda-forge
cairo                     1.18.0               h3faef2a_0    conda-forge
certifi                   2024.2.2           pyhd8ed1ab_0    conda-forge
cffi                      1.16.0           py39h7a31438_0    conda-forge
chardet                   5.2.0            py39hf3d152e_1    conda-forge
charset-normalizer        3.3.2              pyhd8ed1ab_0    conda-forge
click                     8.1.7           unix_pyh707e725_0    conda-forge
colorama                  0.4.6              pyhd8ed1ab_0    conda-forge
comm                      0.2.1              pyhd8ed1ab_0    conda-forge
contextlib2               21.6.0             pyhd8ed1ab_0    conda-forge
contourpy                 1.2.0            py39h7633fee_0    conda-forge
cryptography              42.0.2           py39he6105cc_0    conda-forge
cuda-cudart               11.7.99                       0    nvidia
cuda-cupti                11.7.101                      0    nvidia
cuda-libraries            11.7.1                        0    nvidia
cuda-nvrtc                11.7.99                       0    nvidia
cuda-nvtx                 11.7.91                       0    nvidia
cuda-runtime              11.7.1                        0    nvidia
cudatoolkit               11.8.0              h4ba93d1_13    conda-forge
cycler                    0.12.1             pyhd8ed1ab_0    conda-forge
cyrus-sasl                2.1.28               h52b45da_1    defaults
dataclasses               0.8                pyhc8e2a94_3    conda-forge
dbus                      1.13.18              hb2f20db_0    defaults
debugpy                   1.8.1            py39h3d6467e_0    conda-forge
decorator                 5.1.1              pyhd8ed1ab_0    conda-forge
defusedxml                0.7.1              pyhd8ed1ab_0    conda-forge
deprecated                1.2.14             pyh1a96a4e_0    conda-forge
dllogger                  1.0.0                    pypi_0    pypi
dm-tree                   0.1.8            py39h60f6b12_2    conda-forge
docker-pycreds            0.4.0                      py_0    conda-forge
entrypoints               0.4                pyhd8ed1ab_0    conda-forge
exceptiongroup            1.2.0              pyhd8ed1ab_2    conda-forge
executing                 2.0.1              pyhd8ed1ab_0    conda-forge
expat                     2.5.0                hcb278e6_1    conda-forge
fair-esm                  2.0.1                    pypi_0    pypi
fairscale                 0.4.13                   pypi_0    pypi
font-ttf-dejavu-sans-mono 2.37                 hab24e00_0    conda-forge
font-ttf-inconsolata      3.000                h77eed37_0    conda-forge
font-ttf-source-code-pro  2.038                h77eed37_0    conda-forge
font-ttf-ubuntu           0.83                 h77eed37_1    conda-forge
fontconfig                2.14.2               h14ed4e7_0    conda-forge
fonts-conda-ecosystem     1                             0    conda-forge
fonts-conda-forge         1                             0    conda-forge
fonttools                 4.48.1           py39hd1e30aa_0    conda-forge
fqdn                      1.5.1              pyhd8ed1ab_0    conda-forge
freetype                  2.12.1               h267a509_2    conda-forge
freetype-py               2.3.0              pyhd8ed1ab_0    conda-forge
frozenlist                1.4.1            py39hd1e30aa_0    conda-forge
fsspec                    2024.2.0                 pypi_0    pypi
fvcore                    0.1.5.post20221221    pyhd8ed1ab_0    conda-forge
gettext                   0.21.1               h27087fc_0    conda-forge
gitdb                     4.0.11             pyhd8ed1ab_0    conda-forge
gitpython                 3.1.41             pyhd8ed1ab_0    conda-forge
glib                      2.78.3               hfc55251_0    conda-forge
glib-tools                2.78.3               hfc55251_0    conda-forge
google-auth               2.27.0             pyhca7485f_0    conda-forge
google-auth-oauthlib      1.2.0              pyhd8ed1ab_0    conda-forge
greenlet                  3.0.3            py39h3d6467e_0    conda-forge
grpcio                    1.60.1           py39h174d805_0    conda-forge
gst-plugins-base          1.14.1               h6a678d5_1    defaults
gstreamer                 1.14.1               h5eee18b_1    defaults
h11                       0.14.0             pyhd8ed1ab_0    conda-forge
h2                        4.1.0            py39hf3d152e_0    conda-forge
hpack                     4.0.0              pyh9f0ad1d_0    conda-forge
httpcore                  1.0.2              pyhd8ed1ab_0    conda-forge
httpx                     0.26.0             pyhd8ed1ab_0    conda-forge
hydra-core                1.1.1              pyhd8ed1ab_0    conda-forge
hyperframe                6.0.1              pyhd8ed1ab_0    conda-forge
icu                       73.2                 h59595ed_0    conda-forge
idna                      3.6                pyhd8ed1ab_0    conda-forge
importlib-metadata        7.0.1              pyha770c72_0    conda-forge
importlib-resources       6.1.1              pyhd8ed1ab_0    conda-forge
importlib_metadata        7.0.1                hd8ed1ab_0    conda-forge
importlib_resources       6.1.1              pyhd8ed1ab_0    conda-forge
iniconfig                 2.0.0              pyhd8ed1ab_0    conda-forge
iopath                    0.1.9              pyhd8ed1ab_0    conda-forge
ipykernel                 6.29.2             pyhd33586a_0    conda-forge
ipython                   8.18.1             pyh707e725_3    conda-forge
ipywidgets                8.1.2              pyhd8ed1ab_0    conda-forge
isoduration               20.11.0            pyhd8ed1ab_0    conda-forge
jedi                      0.19.1             pyhd8ed1ab_0    conda-forge
jinja2                    3.1.3              pyhd8ed1ab_0    conda-forge
jpeg                      9e                   h0b41bf4_3    conda-forge
json5                     0.9.14             pyhd8ed1ab_0    conda-forge
jsonpointer               2.4              py39hf3d152e_3    conda-forge
jsonschema                4.21.1             pyhd8ed1ab_0    conda-forge
jsonschema-specifications 2023.12.1          pyhd8ed1ab_0    conda-forge
jsonschema-with-format-nongpl 4.21.1             pyhd8ed1ab_0    conda-forge
jupyter                   1.0.0            py39hf3d152e_9    conda-forge
jupyter-lsp               2.2.2              pyhd8ed1ab_0    conda-forge
jupyter_client            8.6.0              pyhd8ed1ab_0    conda-forge
jupyter_console           6.6.3              pyhd8ed1ab_0    conda-forge
jupyter_core              5.7.1            py39hf3d152e_0    conda-forge
jupyter_events            0.9.0              pyhd8ed1ab_0    conda-forge
jupyter_server            2.12.5             pyhd8ed1ab_0    conda-forge
jupyter_server_terminals  0.5.2              pyhd8ed1ab_0    conda-forge
jupyterlab                4.1.1              pyhd8ed1ab_0    conda-forge
jupyterlab_pygments       0.3.0              pyhd8ed1ab_1    conda-forge
jupyterlab_server         2.25.2             pyhd8ed1ab_0    conda-forge
jupyterlab_widgets        3.0.10             pyhd8ed1ab_0    conda-forge
keyutils                  1.6.1                h166bdaf_0    conda-forge
kiwisolver                1.4.5            py39h7633fee_1    conda-forge
krb5                      1.20.1               h81ceb04_0    conda-forge
lcms2                     2.15                 hfd0df8a_0    conda-forge
ld_impl_linux-64          2.40                 h41732ed_0    conda-forge
lerc                      3.0                  h9c3ff4c_0    conda-forge
libabseil                 20230802.1      cxx17_h59595ed_0    conda-forge
libblas                   3.9.0            21_linux64_mkl    conda-forge
libboost                  1.82.0               h6fcfa73_6    conda-forge
libboost-python           1.82.0           py39hda80f44_6    conda-forge
libbrotlicommon           1.1.0                hd590300_1    conda-forge
libbrotlidec              1.1.0                hd590300_1    conda-forge
libbrotlienc              1.1.0                hd590300_1    conda-forge
libcblas                  3.9.0            21_linux64_mkl    conda-forge
libclang                  14.0.6          default_h7634d5b_1    conda-forge
libclang13                14.0.6          default_h9986a30_1    conda-forge
libcublas                 11.10.3.66                    0    nvidia
libcufft                  10.7.2.124           h4fbf590_0    nvidia
libcufile                 1.8.1.2                       0    nvidia
libcups                   2.4.2                h2d74bed_1    defaults
libcurand                 10.3.4.107                    0    nvidia
libcusolver               11.4.0.1                      0    nvidia
libcusparse               11.7.4.91                     0    nvidia
libdeflate                1.17                 h0b41bf4_0    conda-forge
libedit                   3.1.20230828         h5eee18b_0    defaults
libexpat                  2.5.0                hcb278e6_1    conda-forge
libffi                    3.4.4                h6a678d5_0    defaults
libgcc-ng                 13.2.0               h807b86a_5    conda-forge
libgfortran-ng            13.2.0               h69a702a_5    conda-forge
libgfortran5              13.2.0               ha4646dd_5    conda-forge
libglib                   2.78.3               h783c2da_0    conda-forge
libgrpc                   1.60.1               h74775cd_0    conda-forge
libhwloc                  2.9.3           default_h554bfaf_1009    conda-forge
libiconv                  1.17                 hd590300_2    conda-forge
liblapack                 3.9.0            21_linux64_mkl    conda-forge
liblapacke                3.9.0            21_linux64_mkl    conda-forge
libllvm14                 14.0.6               hcd5def8_4    conda-forge
libnpp                    11.7.4.75                     0    nvidia
libnsl                    2.0.1                hd590300_0    conda-forge
libnvjpeg                 11.8.0.2                      0    nvidia
libpng                    1.6.42               h2797004_0    conda-forge
libpq                     12.17                hdbd6064_0    defaults
libprotobuf               4.25.1               hf27288f_1    conda-forge
libre2-11                 2023.06.02           h7a70373_0    conda-forge
libsodium                 1.0.18               h36c2ea0_1    conda-forge
libsqlite                 3.45.1               h2797004_0    conda-forge
libstdcxx-ng              13.2.0               h7e041cc_5    conda-forge
libtiff                   4.5.1                h6a678d5_0    defaults
libuuid                   2.38.1               h0b41bf4_0    conda-forge
libwebp-base              1.3.2                hd590300_0    conda-forge
libxcb                    1.15                 h0b41bf4_0    conda-forge
libxcrypt                 4.4.36               hd590300_1    conda-forge
libxkbcommon              1.6.0                hd429924_1    conda-forge
libxml2                   2.12.5               h232c23b_0    conda-forge
libzlib                   1.2.13               hd590300_5    conda-forge
lightning-utilities       0.10.1                   pypi_0    pypi
llvm-openmp               17.0.6               h4dfa4b3_0    conda-forge
markdown                  3.5.2              pyhd8ed1ab_0    conda-forge
markupsafe                2.1.5            py39hd1e30aa_0    conda-forge
matplotlib-base           3.8.2            py39he9076e7_0    conda-forge
matplotlib-inline         0.1.6              pyhd8ed1ab_0    conda-forge
mendeleev                 0.15.0                   pypi_0    pypi
mistune                   3.0.2              pyhd8ed1ab_0    conda-forge
mkl                       2024.0.0         ha957f24_49657    conda-forge
mkl-devel                 2024.0.0         ha770c72_49657    conda-forge
mkl-include               2024.0.0         ha957f24_49657    conda-forge
ml-collections            0.1.1              pyhd8ed1ab_0    conda-forge
msgpack-numpy             0.4.8              pyhd8ed1ab_0    conda-forge
msgpack-python            1.0.7            py39h7633fee_0    conda-forge
multidict                 6.0.5            py39hd1e30aa_0    conda-forge
munkres                   1.1.4              pyh9f0ad1d_0    conda-forge
mysql                     5.7.24               h721c034_2    defaults
nbclient                  0.8.0              pyhd8ed1ab_0    conda-forge
nbconvert                 7.16.0             pyhd8ed1ab_0    conda-forge
nbconvert-core            7.16.0             pyhd8ed1ab_0    conda-forge
nbconvert-pandoc          7.16.0             pyhd8ed1ab_0    conda-forge
nbformat                  5.9.2              pyhd8ed1ab_0    conda-forge
ncurses                   6.4                  h59595ed_2    conda-forge
nest-asyncio              1.6.0              pyhd8ed1ab_0    conda-forge
networkx                  3.2.1              pyhd8ed1ab_0    conda-forge
neuralplexer              0.1.0                     dev_0    <develop>
notebook                  7.1.0              pyhd8ed1ab_0    conda-forge
notebook-shim             0.2.3              pyhd8ed1ab_0    conda-forge
numpy                     1.26.4           py39h474f0d3_0    conda-forge
oauthlib                  3.2.2              pyhd8ed1ab_0    conda-forge
omegaconf                 2.1.1            py39hf3d152e_1    conda-forge
openbabel                 3.1.1            py39h2d01fe1_9    conda-forge
openfold                  1.0.1                    pypi_0    pypi
openjpeg                  2.5.0                hfec8fc6_2    conda-forge
openssl                   3.2.1                hd590300_0    conda-forge
overrides                 7.7.0              pyhd8ed1ab_0    conda-forge
packaging                 23.2               pyhd8ed1ab_0    conda-forge
pandas                    2.2.0            py39hddac248_0    conda-forge
pandoc                    3.1.11.1             ha770c72_0    conda-forge
pandocfilters             1.5.0              pyhd8ed1ab_0    conda-forge
parso                     0.8.3              pyhd8ed1ab_0    conda-forge
pathtools                 0.1.2                      py_1    conda-forge
pcre2                     10.42                hcad00b1_0    conda-forge
perl                      5.32.1          7_hd590300_perl5    conda-forge
pexpect                   4.9.0              pyhd8ed1ab_0    conda-forge
pickleshare               0.7.5           py39hde42818_1002    conda-forge
pillow                    10.2.0           py39h5eee18b_0    defaults
pip                       24.0               pyhd8ed1ab_0    conda-forge
pixman                    0.43.2               h59595ed_0    conda-forge
pkgutil-resolve-name      1.3.10             pyhd8ed1ab_1    conda-forge
platformdirs              4.2.0              pyhd8ed1ab_0    conda-forge
pluggy                    1.4.0              pyhd8ed1ab_0    conda-forge
ply                       3.11                       py_1    conda-forge
portalocker               2.8.2            py39hf3d152e_1    conda-forge
power-spherical           0.1.0                    pypi_0    pypi
prody                     2.4.0            py39h227be39_0    conda-forge
prometheus_client         0.19.0             pyhd8ed1ab_0    conda-forge
prompt-toolkit            3.0.43           py39h06a4308_0    defaults
prompt_toolkit            3.0.43               hd3eb1b0_0    defaults
protobuf                  4.25.1           py39h60f6b12_0    conda-forge
psutil                    5.9.8            py39hd1e30aa_0    conda-forge
pthread-stubs             0.4               h36c2ea0_1001    conda-forge
ptyprocess                0.7.0              pyhd3deb0d_0    conda-forge
pure_eval                 0.2.2              pyhd8ed1ab_0    conda-forge
pyasn1                    0.5.1              pyhd8ed1ab_0    conda-forge
pyasn1-modules            0.3.0              pyhd8ed1ab_0    conda-forge
pycairo                   1.26.0           py39hc92de75_0    conda-forge
pycparser                 2.21               pyhd8ed1ab_0    conda-forge
pyfiglet                  0.8.post1                pypi_0    pypi
pygments                  2.17.2             pyhd8ed1ab_0    conda-forge
pyjwt                     2.8.0              pyhd8ed1ab_1    conda-forge
pyopenssl                 24.0.0             pyhd8ed1ab_0    conda-forge
pyparsing                 3.1.1              pyhd8ed1ab_0    conda-forge
pypdb                     2.3                pyhd8ed1ab_0    conda-forge
pyqt                      5.15.10          py39h6a678d5_0    defaults
pyqt5-sip                 12.13.0          py39h5eee18b_0    defaults
pysocks                   1.7.1            py39hf3d152e_5    conda-forge
pytest                    8.0.0              pyhd8ed1ab_0    conda-forge
python                    3.9.18          h0755675_1_cpython    conda-forge
python-dateutil           2.8.2              pyhd8ed1ab_0    conda-forge
python-fastjsonschema     2.19.1             pyhd8ed1ab_0    conda-forge
python-json-logger        2.0.7              pyhd8ed1ab_0    conda-forge
python-lmdb               1.4.1            py39h2926eaa_1    conda-forge
python-tzdata             2024.1             pyhd8ed1ab_0    conda-forge
python_abi                3.9                      4_cp39    conda-forge
pytorch                   1.13.1          py3.9_cuda11.7_cudnn8.5.0_0    pytorch
pytorch-cuda              11.7                 h778d358_5    pytorch
pytorch-lightning         1.9.5                    pypi_0    pypi
pytorch-mutex             1.0                        cuda    pytorch
pytorch3d                 0.7.5           py39_cu117_pyt1131    pytorch3d
pytz                      2024.1             pyhd8ed1ab_0    conda-forge
pyu2f                     0.1.5              pyhd8ed1ab_0    conda-forge
pyyaml                    6.0.1            py39hd1e30aa_1    conda-forge
pyzmq                     25.1.2           py39h8c080ef_0    conda-forge
qt-main                   5.15.2              h53bd1ea_10    defaults
qtconsole                 5.5.1              pyhd8ed1ab_0    conda-forge
qtconsole-base            5.5.1              pyha770c72_0    conda-forge
qtpy                      2.4.1              pyhd8ed1ab_0    conda-forge
rdkit                     2023.09.5        py39hce5ca95_0    conda-forge
re2                       2023.06.02           h2873b5e_0    conda-forge
readline                  8.2                  h8228510_1    conda-forge
referencing               0.33.0             pyhd8ed1ab_0    conda-forge
reportlab                 4.1.0            py39hd1e30aa_0    conda-forge
requests                  2.31.0             pyhd8ed1ab_0    conda-forge
requests-oauthlib         1.3.1              pyhd8ed1ab_0    conda-forge
rfc3339-validator         0.1.4              pyhd8ed1ab_0    conda-forge
rfc3986-validator         0.1.1              pyh9f0ad1d_0    conda-forge
rlpycairo                 0.2.0              pyhd8ed1ab_0    conda-forge
rmsd                      1.5.1              pyhd8ed1ab_0    conda-forge
rpds-py                   0.17.1           py39h9fdd4d6_0    conda-forge
rsa                       4.9                pyhd8ed1ab_0    conda-forge
scipy                     1.12.0           py39h474f0d3_2    conda-forge
seaborn                   0.13.2                   pypi_0    pypi
send2trash                1.8.2              pyh41d4057_0    conda-forge
sentry-sdk                1.40.4             pyhd8ed1ab_0    conda-forge
setproctitle              1.3.3            py39hd1e30aa_0    conda-forge
setuptools                69.0.3             pyhd8ed1ab_0    conda-forge
sip                       6.7.12           py39h3d6467e_0    conda-forge
six                       1.16.0             pyh6c4a22f_0    conda-forge
smmap                     5.0.0              pyhd8ed1ab_0    conda-forge
sniffio                   1.3.0              pyhd8ed1ab_0    conda-forge
soupsieve                 2.5                pyhd8ed1ab_1    conda-forge
sqlalchemy                2.0.27           py39hd1e30aa_0    conda-forge
sqlite                    3.45.1               h2c6b66d_0    conda-forge
stack_data                0.6.2              pyhd8ed1ab_0    conda-forge
tabulate                  0.9.0              pyhd8ed1ab_1    conda-forge
tbb                       2021.11.0            h00ab1b0_1    conda-forge
tensorboard               2.15.2             pyhd8ed1ab_0    conda-forge
tensorboard-data-server   0.7.0            py39hd4f0224_1    conda-forge
termcolor                 2.4.0              pyhd8ed1ab_0    conda-forge
terminado                 0.18.0             pyh0d859eb_0    conda-forge
tinycss2                  1.2.1              pyhd8ed1ab_0    conda-forge
tk                        8.6.13          noxft_h4845f30_101    conda-forge
tmalign                   20170708             h1c9e865_6    bioconda
tomli                     2.0.1              pyhd8ed1ab_0    conda-forge
torch-scatter             2.1.0                    pypi_0    pypi
torchmetrics              1.3.1                    pypi_0    pypi
torchvision               0.14.1                   pypi_0    pypi
tornado                   6.3.3            py39hd1e30aa_1    conda-forge
tqdm                      4.66.2             pyhd8ed1ab_0    conda-forge
traitlets                 5.14.1             pyhd8ed1ab_0    conda-forge
types-python-dateutil     2.8.19.20240106    pyhd8ed1ab_0    conda-forge
typing-extensions         4.9.0                hd8ed1ab_0    conda-forge
typing_extensions         4.9.0              pyha770c72_0    conda-forge
typing_utils              0.1.0              pyhd8ed1ab_0    conda-forge
tzdata                    2024a                h0c530f3_0    conda-forge
unicodedata2              15.1.0           py39hd1e30aa_0    conda-forge
uri-template              1.3.0              pyhd8ed1ab_0    conda-forge
urllib3                   2.2.0              pyhd8ed1ab_0    conda-forge
vim                       9.1.0041        py39pl5321hb4338c2_0    conda-forge
wandb                     0.16.3             pyhd8ed1ab_0    conda-forge
wcwidth                   0.2.13             pyhd8ed1ab_0    conda-forge
webcolors                 1.13               pyhd8ed1ab_0    conda-forge
webencodings              0.5.1              pyhd8ed1ab_2    conda-forge
websocket-client          1.7.0              pyhd8ed1ab_0    conda-forge
werkzeug                  3.0.1              pyhd8ed1ab_0    conda-forge
wheel                     0.42.0             pyhd8ed1ab_0    conda-forge
widgetsnbextension        4.0.10             pyhd8ed1ab_0    conda-forge
wrapt                     1.16.0           py39hd1e30aa_0    conda-forge
xkeyboard-config          2.41                 hd590300_0    conda-forge
xorg-kbproto              1.0.7             h7f98852_1002    conda-forge
xorg-libice               1.1.1                hd590300_0    conda-forge
xorg-libsm                1.2.4                h7391055_0    conda-forge
xorg-libx11               1.8.7                h8ee46fc_0    conda-forge
xorg-libxau               1.0.11               hd590300_0    conda-forge
xorg-libxdmcp             1.1.3                h7f98852_0    conda-forge
xorg-libxext              1.3.4                h0b41bf4_2    conda-forge
xorg-libxrender           0.9.11               hd590300_0    conda-forge
xorg-libxt                1.3.0                hd590300_1    conda-forge
xorg-renderproto          0.11.1            h7f98852_1002    conda-forge
xorg-xextproto            7.3.0             h0b41bf4_1003    conda-forge
xorg-xproto               7.0.31            h7f98852_1007    conda-forge
xz                        5.4.5                h5eee18b_0    defaults
yacs                      0.1.8              pyhd8ed1ab_0    conda-forge
yaml                      0.2.5                h7f98852_2    conda-forge
yarl                      1.9.4            py39hd1e30aa_0    conda-forge
zeromq                    4.3.5                h59595ed_0    conda-forge
zipp                      3.17.0             pyhd8ed1ab_0    conda-forge
zlib                      1.2.13               hd590300_5    conda-forge
zstd                      1.5.5                hfc55251_0    conda-forge

If you could attached the output from your conda list from your Neuralplexer env we might be able to see why torch is complaining.

MKCarter commented 1 month ago

OK, after looking at the torch error - it may be that your env has the wrong mkl version installed. This torch error is thrown when mkl 24.1+ is installed - if you can downgrade your mkl to be 24.0.0 then you should fix the bug.

https://github.com/pytorch/pytorch/issues/123097 - see this github issue for more information

danid77 commented 1 month ago

Oh, I'll give it a try and leave a comment afterward. Thank you!

thank! Danid