python - 在 Conda UnsatisfiableError 消息中找不到冲突

Question

尝试在 Docker 中的 conda 中安装 pytorch，并得到 UnsatisfiableError。但是，我在错误消息中找不到任何实际冲突，或者我可能无法正确理解它。使用的 Docker 镜像是 nvidia/cuda:10.1-cudnn7-devel-ubuntu18.04。如果我不指定安装的pytorch版本是不会有问题的。但我确实需要这个版本的 pytorch 来处理一些遗留代码。

这是 conda 命令和错误消息。

(Python3.6) root@0cb9aad73116:/# conda install -c pytorch pytorch=0.3.1
Collecting package metadata (current_repodata.json): done
Solving environment: failed with initial frozen solve. Retrying with flexible solve.
Solving environment: failed with repodata from current_repodata.json, will retry with next repodata source.
Collecting package metadata (repodata.json): done
Solving environment: failed with initial frozen solve. Retrying with flexible solve.
Solving environment: |
Found conflicts! Looking for incompatible packages.
This can take several minutes.  Press CTRL-C to abort.
failed

UnsatisfiableError: The following specifications were found to be incompatible with each other:



Package libgcc-ng conflicts for:
python==3.6.9 -> libgcc-ng[version='>=7.3.0']
zlib -> libgcc-ng[version='>=7.2.0|>=7.3.0']
tk -> libgcc-ng[version='>=7.2.0|>=7.3.0']
xz -> libgcc-ng[version='>=7.2.0']
pytorch=0.3.1 -> libgcc-ng[version='>=5.4.0']
libedit -> libgcc-ng[version='>=7.2.0|>=7.3.0']
libffi -> libgcc-ng[version='>=7.2.0']
ncurses -> libgcc-ng[version='>=7.2.0|>=7.3.0']
sqlite -> libgcc-ng[version='>=7.2.0|>=7.3.0']
readline -> libgcc-ng[version='>=7.2.0|>=7.3.0']
openssl -> libgcc-ng[version='>=7.2.0|>=7.3.0']
Package libstdcxx-ng conflicts for:
ncurses -> libstdcxx-ng[version='>=7.2.0|>=7.3.0']
pytorch=0.3.1 -> libstdcxx-ng[version='>=5.4.0']
python==3.6.9 -> libstdcxx-ng[version='>=7.3.0']
libffi -> libstdcxx-ng[version='>=7.2.0']
Package xz conflicts for:
python==3.6.9 -> xz[version='>=5.2.4,<6.0a0']
Package cudnn conflicts for:
pytorch=0.3.1 -> cudnn[version='7.0.*|>=7.0.5,<=8.0a0']
Package nccl conflicts for:
pytorch=0.3.1 -> nccl[version='<2']
Package setuptools conflicts for:
wheel -> setuptools
pip -> setuptools
Package zlib conflicts for:
tk -> zlib[version='>=1.2.11,<1.3.0a0']
python==3.6.9 -> zlib[version='>=1.2.11,<1.3.0a0']
Package ca-certificates conflicts for:
openssl -> ca-certificates
Package libffi conflicts for:
python==3.6.9 -> libffi[version='>=3.2.1,<4.0a0']
Package cudatoolkit conflicts for:
pytorch=0.3.1 -> cudatoolkit[version='8.*|8.0.*']
Package _libgcc_mutex conflicts for:
libgcc-ng -> _libgcc_mutex=[build=main]
Package numpy conflicts for:
pytorch=0.3.1 -> numpy[version='>=1.11|>=1.11.3,<2.0a0']
Package openssl conflicts for:
python==3.6.9 -> openssl[version='>=1.1.1c,<1.1.2a']
Package libedit conflicts for:
sqlite -> libedit[version='>=3.1.20170329,<3.2.0a0|>=3.1.20181209,<3.2.0a0']
Package ncurses conflicts for:
python==3.6.9 -> ncurses[version='>=6.1,<7.0a0']
readline -> ncurses[version='6.0.*|>=6.0,<7.0a0|>=6.1,<7.0a0']
libedit -> ncurses[version='6.0.*|>=6.1,<7.0a0']
Package cffi conflicts for:
pytorch=0.3.1 -> cffi
Package sqlite conflicts for:
python==3.6.9 -> sqlite[version='>=3.29.0,<4.0a0']
Package * conflicts for:
pytorch=0.3.1 -> *[track_features=cuda90]
Package tk conflicts for:
python==3.6.9 -> tk[version='>=8.6.8,<8.7.0a0']
Package wheel conflicts for:
pip -> wheel
Package certifi conflicts for:
setuptools -> certifi[version='>=2016.09|>=2016.9.26']
Package mkl conflicts for:
pytorch=0.3.1 -> mkl[version='>=2018|>=2018.0.2,<2019.0a0']
Package readline conflicts for:
python==3.6.9 -> readline[version='>=7.0,<8.0a0']
Package pip conflicts for:
python==3.6.9 -> pip

已安装的软件包

(Python3.6) root@0cb9aad73116:/# conda list
# packages in environment at /opt/conda/envs/Python3.6:
#
# Name                    Version                   Build  Channel
_libgcc_mutex             0.1                        main
ca-certificates           2019.11.27                    0
certifi                   2019.11.28               py36_0
libedit                   3.1.20181209         hc058e9b_0
libffi                    3.2.1                hd88cf55_4
libgcc-ng                 9.1.0                hdf63c60_0
libstdcxx-ng              9.1.0                hdf63c60_0
ncurses                   6.1                  he6710b0_1
openssl                   1.1.1d               h7b6447c_3
pip                       19.3.1                   py36_0
python                    3.6.9                h265db76_0
readline                  7.0                  h7b6447c_5
setuptools                42.0.2                   py36_0
sqlite                    3.30.1               h7b6447c_0
tk                        8.6.8                hbc83047_0
wheel                     0.33.6                   py36_0
xz                        5.2.4                h14c3975_4
zlib                      1.2.11               h7b6447c_3

如果使用 Docker 镜像 continuumio/miniconda3:4.7.12，仍然会出现类似错误。

Answer 1

docker run -it nvidia/cuda:10.1-cudnn7-devel-ubuntu18.04 bash
apt-get update
apt install wget -y
wget https://repo.continuum.io/archive/Anaconda3-4.3.0-Linux-x86_64.sh 
bash Anaconda3-4.3.0-Linux-x86_64.sh
[Enter]
yes
[Enter]
yes
. /root/.bashrc
conda install mkl
y
conda install -c pytorch pytorch=0.3.1
y
conda list|grep pytorch

pytorch 0.3.1 py36_cuda8.0.61_cudnn7.1.2_3 pytorch


root@dacfe958940b:/# bash
(base) root@dacfe958940b:/# python
Python 3.6.3 |Anaconda 自定义(64 位)| (默认，2017 年 10 月 13 日 12:02:49)
Linux 上的 [GCC 7.2.0]
输入“帮助”、“版权”、“制作人员”或“许可证”以获取更多信息。
进口 torch
打印( torch .__版本__)
0.3.1.post3