专栏/env1

env1

2021年12月15日 15:35--浏览 · --点赞 · --评论
粉丝:697文章:94

Part 1: create the conda env for the project
(base) ren2@Ren2:~/data2/mengya/mengya_code/main_ImageCaptioning.pytorch$ conda create -n Captioning_Zoo python=3.8
Collecting package metadata (current_repodata.json): done
Solving environment: done


==> WARNING: A newer version of conda exists. <==
  current version: 4.10.1
  latest version: 4.11.0

Please update conda by running

    $ conda update -n base -c defaults conda



## Package Plan ##

  environment location: /home/ren2/anaconda3/envs/Captioning_Zoo

  added / updated specs:
    - python=3.8


The following NEW packages will be INSTALLED:

  _libgcc_mutex      pkgs/main/linux-64::_libgcc_mutex-0.1-main
  _openmp_mutex      pkgs/main/linux-64::_openmp_mutex-4.5-1_gnu
  ca-certificates    pkgs/main/linux-64::ca-certificates-2021.10.26-h06a4308_2
  certifi            pkgs/main/linux-64::certifi-2021.10.8-py38h06a4308_0
  ld_impl_linux-64   pkgs/main/linux-64::ld_impl_linux-64-2.35.1-h7274673_9
  libffi             pkgs/main/linux-64::libffi-3.3-he6710b0_2
  libgcc-ng          pkgs/main/linux-64::libgcc-ng-9.3.0-h5101ec6_17
  libgomp            pkgs/main/linux-64::libgomp-9.3.0-h5101ec6_17
  libstdcxx-ng       pkgs/main/linux-64::libstdcxx-ng-9.3.0-hd4cf53a_17
  ncurses            pkgs/main/linux-64::ncurses-6.3-h7f8727e_2
  openssl            pkgs/main/linux-64::openssl-1.1.1l-h7f8727e_0
  pip                pkgs/main/linux-64::pip-21.2.4-py38h06a4308_0
  python             pkgs/main/linux-64::python-3.8.12-h12debd9_0
  readline           pkgs/main/linux-64::readline-8.1-h27cfd23_0
  setuptools         pkgs/main/linux-64::setuptools-58.0.4-py38h06a4308_0
  sqlite             pkgs/main/linux-64::sqlite-3.36.0-hc218d9a_0
  tk                 pkgs/main/linux-64::tk-8.6.11-h1ccaba5_0
  wheel              pkgs/main/noarch::wheel-0.37.0-pyhd3eb1b0_1
  xz                 pkgs/main/linux-64::xz-5.2.5-h7b6447c_0
  zlib               pkgs/main/linux-64::zlib-1.2.11-h7b6447c_3


Proceed ([y]/n)?

Preparing transaction: done
Verifying transaction: done
Executing transaction: done
#
# To activate this environment, use
#
#     $ conda activate Captioning_Zoo
#
# To deactivate an active environment, use
#
#     $ conda deactivate

(base) ren2@Ren2:~/data2/mengya/mengya_code/main_ImageCaptioning.pytorch$ conda activate Captioning_Zoo
(Captioning_Zoo) ren2@Ren2:~/data2/mengya/mengya_code/main_ImageCaptioning.pytorch$ conda list
# packages in environment at /home/ren2/anaconda3/envs/Captioning_Zoo:
#
# Name                    Version                   Build  Channel
_libgcc_mutex             0.1                        main  
_openmp_mutex             4.5                       1_gnu  
ca-certificates           2021.10.26           h06a4308_2  
certifi                   2021.10.8        py38h06a4308_0  
ld_impl_linux-64          2.35.1               h7274673_9  
libffi                    3.3                  he6710b0_2  
libgcc-ng                 9.3.0               h5101ec6_17  
libgomp                   9.3.0               h5101ec6_17  
libstdcxx-ng              9.3.0               hd4cf53a_17  
ncurses                   6.3                  h7f8727e_2  
openssl                   1.1.1l               h7f8727e_0  
pip                       21.2.4           py38h06a4308_0  
python                    3.8.12               h12debd9_0  
readline                  8.1                  h27cfd23_0  
setuptools                58.0.4           py38h06a4308_0  
sqlite                    3.36.0               hc218d9a_0  
tk                        8.6.11               h1ccaba5_0  
wheel                     0.37.0             pyhd3eb1b0_1  
xz                        5.2.5                h7b6447c_0  
zlib                      1.2.11               h7b6447c_3  
(Captioning_Zoo) ren2@Ren2:~/data2/mengya/mengya_code/main_ImageCaptioning.pytorch$ conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch
Collecting package metadata (current_repodata.json): done
Solving environment: done


==> WARNING: A newer version of conda exists. <==
  current version: 4.10.1
  latest version: 4.11.0

Please update conda by running

    $ conda update -n base -c defaults conda



## Package Plan ##

  environment location: /home/ren2/anaconda3/envs/Captioning_Zoo

  added / updated specs:
    - cudatoolkit=11.3
    - pytorch
    - torchaudio
    - torchvision


The following packages will be downloaded:

    package                    |            build
    ---------------------------|-----------------
    torchaudio-0.10.0          |       py38_cu113         4.5 MB  pytorch
    ------------------------------------------------------------
                                           Total:         4.5 MB

The following NEW packages will be INSTALLED:

  blas               pkgs/main/linux-64::blas-1.0-mkl
  bzip2              pkgs/main/linux-64::bzip2-1.0.8-h7b6447c_0
  cudatoolkit        pkgs/main/linux-64::cudatoolkit-11.3.1-h2bc3f7f_2
  ffmpeg             pytorch/linux-64::ffmpeg-4.3-hf484d3e_0
  freetype           pkgs/main/linux-64::freetype-2.11.0-h70c0345_0
  giflib             pkgs/main/linux-64::giflib-5.2.1-h7b6447c_0
  gmp                pkgs/main/linux-64::gmp-6.2.1-h2531618_2
  gnutls             pkgs/main/linux-64::gnutls-3.6.15-he1e5248_0
  intel-openmp       pkgs/main/linux-64::intel-openmp-2021.4.0-h06a4308_3561
  jpeg               pkgs/main/linux-64::jpeg-9d-h7f8727e_0
  lame               pkgs/main/linux-64::lame-3.100-h7b6447c_0
  lcms2              pkgs/main/linux-64::lcms2-2.12-h3be6417_0
  libiconv           pkgs/main/linux-64::libiconv-1.15-h63c8f33_5
  libidn2            pkgs/main/linux-64::libidn2-2.3.2-h7f8727e_0
  libpng             pkgs/main/linux-64::libpng-1.6.37-hbc83047_0
  libtasn1           pkgs/main/linux-64::libtasn1-4.16.0-h27cfd23_0
  libtiff            pkgs/main/linux-64::libtiff-4.2.0-h85742a9_0
  libunistring       pkgs/main/linux-64::libunistring-0.9.10-h27cfd23_0
  libuv              pkgs/main/linux-64::libuv-1.40.0-h7b6447c_0
  libwebp            pkgs/main/linux-64::libwebp-1.2.0-h89dd481_0
  libwebp-base       pkgs/main/linux-64::libwebp-base-1.2.0-h27cfd23_0
  lz4-c              pkgs/main/linux-64::lz4-c-1.9.3-h295c915_1
  mkl                pkgs/main/linux-64::mkl-2021.4.0-h06a4308_640
  mkl-service        pkgs/main/linux-64::mkl-service-2.4.0-py38h7f8727e_0
  mkl_fft            pkgs/main/linux-64::mkl_fft-1.3.1-py38hd3c417c_0
  mkl_random         pkgs/main/linux-64::mkl_random-1.2.2-py38h51133e4_0
  nettle             pkgs/main/linux-64::nettle-3.7.3-hbbd107a_1
  numpy              pkgs/main/linux-64::numpy-1.21.2-py38h20f2e39_0
  numpy-base         pkgs/main/linux-64::numpy-base-1.21.2-py38h79a1101_0
  olefile            pkgs/main/noarch::olefile-0.46-pyhd3eb1b0_0
  openh264           pkgs/main/linux-64::openh264-2.1.0-hd408876_0
  pillow             pkgs/main/linux-64::pillow-8.4.0-py38h5aabda8_0
  pytorch            pytorch/linux-64::pytorch-1.10.0-py3.8_cuda11.3_cudnn8.2.0_0
  pytorch-mutex      pytorch/noarch::pytorch-mutex-1.0-cuda
  six                pkgs/main/noarch::six-1.16.0-pyhd3eb1b0_0
  torchaudio         pytorch/linux-64::torchaudio-0.10.0-py38_cu113
  torchvision        pytorch/linux-64::torchvision-0.11.1-py38_cu113
  typing_extensions  pkgs/main/noarch::typing_extensions-3.10.0.2-pyh06a4308_0
  zstd               pkgs/main/linux-64::zstd-1.4.9-haebb681_0


Proceed ([y]/n)?


Downloading and Extracting Packages
torchaudio-0.10.0    | 4.5 MB    | ################################################################################################################################### | 100%
Preparing transaction: done
Verifying transaction: done
Executing transaction: - By downloading and using the CUDA Toolkit conda packages, you accept the terms and conditions of the CUDA End User License Agreement (EULA): https://docs.nvidia.com/cuda/eula/index.html

done
(Captioning_Zoo) ren2@Ren2:~/data2/mengya/mengya_code/main_ImageCaptioning.pytorch$ conda list
# packages in environment at /home/ren2/anaconda3/envs/Captioning_Zoo:
#
# Name                    Version                   Build  Channel
_libgcc_mutex             0.1                        main  
_openmp_mutex             4.5                       1_gnu  
blas                      1.0                         mkl  
bzip2                     1.0.8                h7b6447c_0  
ca-certificates           2021.10.26           h06a4308_2  
certifi                   2021.10.8        py38h06a4308_0  
cudatoolkit               11.3.1               h2bc3f7f_2  
ffmpeg                    4.3                  hf484d3e_0    pytorch
freetype                  2.11.0               h70c0345_0  
giflib                    5.2.1                h7b6447c_0  
gmp                       6.2.1                h2531618_2  
gnutls                    3.6.15               he1e5248_0  
intel-openmp              2021.4.0          h06a4308_3561  
jpeg                      9d                   h7f8727e_0  
lame                      3.100                h7b6447c_0  
lcms2                     2.12                 h3be6417_0  
ld_impl_linux-64          2.35.1               h7274673_9  
libffi                    3.3                  he6710b0_2  
libgcc-ng                 9.3.0               h5101ec6_17  
libgomp                   9.3.0               h5101ec6_17  
libiconv                  1.15                 h63c8f33_5  
libidn2                   2.3.2                h7f8727e_0  
libpng                    1.6.37               hbc83047_0  
libstdcxx-ng              9.3.0               hd4cf53a_17  
libtasn1                  4.16.0               h27cfd23_0  
libtiff                   4.2.0                h85742a9_0  
libunistring              0.9.10               h27cfd23_0  
libuv                     1.40.0               h7b6447c_0  
libwebp                   1.2.0                h89dd481_0  
libwebp-base              1.2.0                h27cfd23_0  
lz4-c                     1.9.3                h295c915_1  
mkl                       2021.4.0           h06a4308_640  
mkl-service               2.4.0            py38h7f8727e_0  
mkl_fft                   1.3.1            py38hd3c417c_0  
mkl_random                1.2.2            py38h51133e4_0  
ncurses                   6.3                  h7f8727e_2  
nettle                    3.7.3                hbbd107a_1  
numpy                     1.21.2           py38h20f2e39_0  
numpy-base                1.21.2           py38h79a1101_0  
olefile                   0.46               pyhd3eb1b0_0  
openh264                  2.1.0                hd408876_0  
openssl                   1.1.1l               h7f8727e_0  
pillow                    8.4.0            py38h5aabda8_0  
pip                       21.2.4           py38h06a4308_0  
python                    3.8.12               h12debd9_0  
pytorch                   1.10.0          py3.8_cuda11.3_cudnn8.2.0_0    pytorch
pytorch-mutex             1.0                        cuda    pytorch
readline                  8.1                  h27cfd23_0  
setuptools                58.0.4           py38h06a4308_0  
six                       1.16.0             pyhd3eb1b0_0  
sqlite                    3.36.0               hc218d9a_0  
tk                        8.6.11               h1ccaba5_0  
torchaudio                0.10.0               py38_cu113    pytorch
torchvision               0.11.1               py38_cu113    pytorch
typing_extensions         3.10.0.2           pyh06a4308_0  
wheel                     0.37.0             pyhd3eb1b0_1  
xz                        5.2.5                h7b6447c_0  
zlib                      1.2.11               h7b6447c_3  
zstd                      1.4.9                haebb681_0  
(Captioning_Zoo) ren2@Ren2:~/data2/mengya/mengya_code/main_ImageCaptioning.pytorch$ python tools/train.py --cfg configs/fc.yml --id fc
Traceback (most recent call last):
  File "tools/train.py", line 8, in <module>
    from torch.utils.tensorboard import SummaryWriter
  File "/home/ren2/anaconda3/envs/Captioning_Zoo/lib/python3.8/site-packages/torch/utils/tensorboard/__init__.py", line 1, in <module>
    import tensorboard
ModuleNotFoundError: No module named 'tensorboard'
(Captioning_Zoo) ren2@Ren2:~/data2/mengya/mengya_code/main_ImageCaptioning.pytorch$ pip install tensorboard
Collecting tensorboard
  Using cached tensorboard-2.7.0-py3-none-any.whl (5.8 MB)
Collecting markdown>=2.6.8
  Using cached Markdown-3.3.6-py3-none-any.whl (97 kB)
Collecting werkzeug>=0.11.15
  Using cached Werkzeug-2.0.2-py3-none-any.whl (288 kB)
Collecting absl-py>=0.4
  Using cached absl_py-1.0.0-py3-none-any.whl (126 kB)
Requirement already satisfied: setuptools>=41.0.0 in /home/ren2/anaconda3/envs/Captioning_Zoo/lib/python3.8/site-packages (from tensorboard) (58.0.4)
Collecting tensorboard-data-server<0.7.0,>=0.6.0
  Using cached tensorboard_data_server-0.6.1-py3-none-manylinux2010_x86_64.whl (4.9 MB)
Collecting google-auth<3,>=1.6.3
  Using cached google_auth-2.3.3-py2.py3-none-any.whl (155 kB)
Collecting requests<3,>=2.21.0
  Using cached requests-2.26.0-py2.py3-none-any.whl (62 kB)
Collecting protobuf>=3.6.0
  Using cached protobuf-3.19.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.1 MB)
Collecting google-auth-oauthlib<0.5,>=0.4.1
  Using cached google_auth_oauthlib-0.4.6-py2.py3-none-any.whl (18 kB)
Collecting tensorboard-plugin-wit>=1.6.0
  Using cached tensorboard_plugin_wit-1.8.0-py3-none-any.whl (781 kB)
Requirement already satisfied: numpy>=1.12.0 in /home/ren2/anaconda3/envs/Captioning_Zoo/lib/python3.8/site-packages (from tensorboard) (1.21.2)
Collecting grpcio>=1.24.3
  Downloading grpcio-1.42.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.0 MB)
     |████████████████████████████████| 4.0 MB 10.5 MB/s
Requirement already satisfied: wheel>=0.26 in /home/ren2/anaconda3/envs/Captioning_Zoo/lib/python3.8/site-packages (from tensorboard) (0.37.0)
Requirement already satisfied: six in /home/ren2/anaconda3/envs/Captioning_Zoo/lib/python3.8/site-packages (from absl-py>=0.4->tensorboard) (1.16.0)
Collecting rsa<5,>=3.1.4
  Using cached rsa-4.8-py3-none-any.whl (39 kB)
Collecting pyasn1-modules>=0.2.1
  Using cached pyasn1_modules-0.2.8-py2.py3-none-any.whl (155 kB)
Collecting cachetools<5.0,>=2.0.0
  Using cached cachetools-4.2.4-py3-none-any.whl (10 kB)
Collecting requests-oauthlib>=0.7.0
  Using cached requests_oauthlib-1.3.0-py2.py3-none-any.whl (23 kB)
Collecting importlib-metadata>=4.4
  Using cached importlib_metadata-4.8.2-py3-none-any.whl (17 kB)
Collecting zipp>=0.5
  Using cached zipp-3.6.0-py3-none-any.whl (5.3 kB)
Collecting pyasn1<0.5.0,>=0.4.6
  Using cached pyasn1-0.4.8-py2.py3-none-any.whl (77 kB)
Requirement already satisfied: certifi>=2017.4.17 in /home/ren2/anaconda3/envs/Captioning_Zoo/lib/python3.8/site-packages (from requests<3,>=2.21.0->tensorboard) (2021.10.8)
Collecting charset-normalizer~=2.0.0
  Using cached charset_normalizer-2.0.9-py3-none-any.whl (39 kB)
Collecting urllib3<1.27,>=1.21.1
  Using cached urllib3-1.26.7-py2.py3-none-any.whl (138 kB)
Collecting idna<4,>=2.5
  Using cached idna-3.3-py3-none-any.whl (61 kB)
Collecting oauthlib>=3.0.0
  Using cached oauthlib-3.1.1-py2.py3-none-any.whl (146 kB)
Installing collected packages: urllib3, pyasn1, idna, charset-normalizer, zipp, rsa, requests, pyasn1-modules, oauthlib, cachetools, requests-oauthlib, importlib-metadata, google-auth, werkzeug, tensorboard-plugin-wit, tensorboard-data-server, protobuf, markdown, grpcio, google-auth-oauthlib, absl-py, tensorboard
Successfully installed absl-py-1.0.0 cachetools-4.2.4 charset-normalizer-2.0.9 google-auth-2.3.3 google-auth-oauthlib-0.4.6 grpcio-1.42.0 idna-3.3 importlib-metadata-4.8.2 markdown-3.3.6 oauthlib-3.1.1 protobuf-3.19.1 pyasn1-0.4.8 pyasn1-modules-0.2.8 requests-2.26.0 requests-oauthlib-1.3.0 rsa-4.8 tensorboard-2.7.0 tensorboard-data-server-0.6.1 tensorboard-plugin-wit-1.8.0 urllib3-1.26.7 werkzeug-2.0.2 zipp-3.6.0
(Captioning_Zoo) ren2@Ren2:~/data2/mengya/mengya_code/main_ImageCaptioning.pytorch$ python tools/train.py --cfg configs/fc.yml --id fc
Traceback (most recent call last):
  File "tools/train.py", line 18, in <module>
    import captioning.utils.opts as opts
ModuleNotFoundError: No module named 'captioning'
(Captioning_Zoo) ren2@Ren2:~/data2/mengya/mengya_code/main_ImageCaptioning.pytorch$ python -m pip install -e .
Obtaining file:///home/ren2/data2/mengya/mengya_code/main_ImageCaptioning.pytorch
Installing collected packages: captioning
  Running setup.py develop for captioning
Successfully installed captioning-0.0.1
(Captioning_Zoo) ren2@Ren2:~/data2/mengya/mengya_code/main_ImageCaptioning.pytorch$ python tools/train.py --cfg configs/fc.yml --id fc
Hugginface transformers not installed; please visit https://github.com/huggingface/transformers
meshed-memory-transformer not installed; please run `pip install git+https://github.com/ruotianluo/meshed-memory-transformer.git`
Traceback (most recent call last):
  File "tools/train.py", line 20, in <module>
    from captioning.data.dataloader import *
  File "/home/ren2/data2/mengya/mengya_code/main_ImageCaptioning.pytorch/captioning/data/dataloader.py", line 6, in <module>
    import h5py
ModuleNotFoundError: No module named 'h5py'
(Captioning_Zoo) ren2@Ren2:~/data2/mengya/mengya_code/main_ImageCaptioning.pytorch$ pip install h5py
Collecting h5py
  Downloading h5py-3.6.0-cp38-cp38-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (4.5 MB)
     |████████████████████████████████| 4.5 MB 11.0 MB/s
Requirement already satisfied: numpy>=1.14.5 in /home/ren2/anaconda3/envs/Captioning_Zoo/lib/python3.8/site-packages (from h5py) (1.21.2)
Installing collected packages: h5py
Successfully installed h5py-3.6.0
(Captioning_Zoo) ren2@Ren2:~/data2/mengya/mengya_code/main_ImageCaptioning.pytorch$ python tools/train.py --cfg configs/fc.yml --id fc
Hugginface transformers not installed; please visit https://github.com/huggingface/transformers
meshed-memory-transformer not installed; please run `pip install git+https://github.com/ruotianluo/meshed-memory-transformer.git`
Traceback (most recent call last):
  File "tools/train.py", line 20, in <module>
    from captioning.data.dataloader import *
  File "/home/ren2/data2/mengya/mengya_code/main_ImageCaptioning.pytorch/captioning/data/dataloader.py", line 7, in <module>
    from lmdbdict import lmdbdict
ModuleNotFoundError: No module named 'lmdbdict'
(Captioning_Zoo) ren2@Ren2:~/data2/mengya/mengya_code/main_ImageCaptioning.pytorch$ pip install lmdbdict
Collecting lmdbdict
  Using cached lmdbdict-0.2.2-py3-none-any.whl (6.0 kB)
Collecting lmdb
  Downloading lmdb-1.2.1-cp38-cp38-manylinux2010_x86_64.whl (306 kB)
     |████████████████████████████████| 306 kB 11.4 MB/s
Installing collected packages: lmdb, lmdbdict
Successfully installed lmdb-1.2.1 lmdbdict-0.2.2
(Captioning_Zoo) ren2@Ren2:~/data2/mengya/mengya_code/main_ImageCaptioning.pytorch$ python tools/train.py --cfg configs/fc.yml --id fc
Hugginface transformers not installed; please visit https://github.com/huggingface/transformers
meshed-memory-transformer not installed; please run `pip install git+https://github.com/ruotianluo/meshed-memory-transformer.git`
Traceback (most recent call last):
  File "tools/train.py", line 21, in <module>
    import skimage.io
ModuleNotFoundError: No module named 'skimage'
(Captioning_Zoo) ren2@Ren2:~/data2/mengya/mengya_code/main_ImageCaptioning.pytorch$ pip install scikit-image
Collecting scikit-image
  Downloading scikit_image-0.19.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (60.7 MB)
     |████████████████████████████████| 60.7 MB 10.5 MB/s
Requirement already satisfied: numpy>=1.17.0 in /home/ren2/anaconda3/envs/Captioning_Zoo/lib/python3.8/site-packages (from scikit-image) (1.21.2)
Requirement already satisfied: pillow!=7.1.0,!=7.1.1,!=8.3.0,>=6.1.0 in /home/ren2/anaconda3/envs/Captioning_Zoo/lib/python3.8/site-packages (from scikit-image) (8.4.0)
Collecting imageio>=2.4.1
  Using cached imageio-2.13.3-py3-none-any.whl (3.3 MB)
Collecting tifffile>=2019.7.26
  Downloading tifffile-2021.11.2-py3-none-any.whl (178 kB)
     |████████████████████████████████| 178 kB 11.1 MB/s
Collecting networkx>=2.2
  Using cached networkx-2.6.3-py3-none-any.whl (1.9 MB)
Collecting scipy>=1.4.1
  Downloading scipy-1.7.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (39.3 MB)
     |████████████████████████████████| 39.3 MB 12.2 MB/s
Collecting packaging>=20.0
  Using cached packaging-21.3-py3-none-any.whl (40 kB)
Collecting PyWavelets>=1.1.1
  Downloading PyWavelets-1.2.0-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.whl (6.3 MB)
     |████████████████████████████████| 6.3 MB 11.0 MB/s
Collecting pyparsing!=3.0.5,>=2.0.2
  Using cached pyparsing-3.0.6-py3-none-any.whl (97 kB)
Installing collected packages: pyparsing, tifffile, scipy, PyWavelets, packaging, networkx, imageio, scikit-image
Successfully installed PyWavelets-1.2.0 imageio-2.13.3 networkx-2.6.3 packaging-21.3 pyparsing-3.0.6 scikit-image-0.19.0 scipy-1.7.3 tifffile-2021.11.2
(Captioning_Zoo) ren2@Ren2:~/data2/mengya/mengya_code/main_ImageCaptioning.pytorch$ python tools/train.py --cfg configs/fc.yml --id fc
Hugginface transformers not installed; please visit https://github.com/huggingface/transformers
meshed-memory-transformer not installed; please run `pip install git+https://github.com/ruotianluo/meshed-memory-transformer.git`
Warning: coco-caption not available
Traceback (most recent call last):
  File "tools/train.py", line 295, in <module>
    opt = opts.parse_opt()
  File "/home/ren2/data2/mengya/mengya_code/main_ImageCaptioning.pytorch/captioning/utils/opts.py", line 232, in parse_opt
    from .config import CfgNode
  File "/home/ren2/data2/mengya/mengya_code/main_ImageCaptioning.pytorch/captioning/utils/config.py", line 7, in <module>
    import yaml
ModuleNotFoundError: No module named 'yaml'
(Captioning_Zoo) ren2@Ren2:~/data2/mengya/mengya_code/main_ImageCaptioning.pytorch$ pip install pyyaml
Collecting pyyaml
  Downloading PyYAML-6.0-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl (701 kB)
     |████████████████████████████████| 701 kB 11.0 MB/s
Installing collected packages: pyyaml
Successfully installed pyyaml-6.0
(Captioning_Zoo) ren2@Ren2:~/data2/mengya/mengya_code/main_ImageCaptioning.pytorch$ python tools/train.py --cfg configs/fc.yml --id fc
Hugginface transformers not installed; please visit https://github.com/huggingface/transformers
meshed-memory-transformer not installed; please run `pip install git+https://github.com/ruotianluo/meshed-memory-transformer.git`
Warning: coco-caption not available
Traceback (most recent call last):
  File "tools/train.py", line 295, in <module>
    opt = opts.parse_opt()
  File "/home/ren2/data2/mengya/mengya_code/main_ImageCaptioning.pytorch/captioning/utils/opts.py", line 232, in parse_opt
    from .config import CfgNode
  File "/home/ren2/data2/mengya/mengya_code/main_ImageCaptioning.pytorch/captioning/utils/config.py", line 8, in <module>
    from yacs.config import CfgNode as _CfgNode
ModuleNotFoundError: No module named 'yacs'
(Captioning_Zoo) ren2@Ren2:~/data2/mengya/mengya_code/main_ImageCaptioning.pytorch$ pip install yacs
Collecting yacs
  Using cached yacs-0.1.8-py3-none-any.whl (14 kB)
Requirement already satisfied: PyYAML in /home/ren2/anaconda3/envs/Captioning_Zoo/lib/python3.8/site-packages (from yacs) (6.0)
Installing collected packages: yacs
Successfully installed yacs-0.1.8
(Captioning_Zoo) ren2@Ren2:~/data2/mengya/mengya_code/main_ImageCaptioning.pytorch$ python tools/train.py --cfg configs/fc.yml --id fc
Hugginface transformers not installed; please visit https://github.com/huggingface/transformers
meshed-memory-transformer not installed; please run `pip install git+https://github.com/ruotianluo/meshed-memory-transformer.git`
Warning: coco-caption not available
DataLoader loading json file:  data/cocotalk.json
vocab size is  9487
DataLoader loading h5 file:  data/cocotalk_fc data/cocotalk_att data/cocotalk_box data/cocotalk_label.h5
max sequence length in data is 16
read 123287 image features
assigned 113287 images to split train
assigned 5000 images to split val
assigned 5000 images to split test
Read data: 0.00609278678894043
/home/ren2/anaconda3/envs/Captioning_Zoo/lib/python3.8/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.
  warnings.warn('Was asked to gather along dimension 0, but all '
iter 0 (epoch 0), train_loss = 9.191, time/batch = 5.047
Read data: 0.00029587745666503906
iter 1 (epoch 0), train_loss = 9.060, time/batch = 0.073
Read data: 0.00022864341735839844
iter 2 (epoch 0), train_loss = 8.898, time/batch = 0.075
Read data: 0.00017642974853515625
iter 3 (epoch 0), train_loss = 8.774, time/batch = 0.065



=====================================================
Part 2: lack other captioning model
pip install matplotlib
pip install -U gensim
pip install git+https://github.com/huggingface/transformers.git
pip install git+https://github.com/ruotianluo/meshed-memory-transformer.git

FileNotFoundError: [Errno 2] No such file or directory: '/coco-caption/pycocoevalcap/wmd/data/GoogleNews-vectors-negative300.bin'
You can download the word2vec: https://s3.amazonaws.com/dl4j-distribution/GoogleNews-vectors-negative300.bin.gz
(Solution is from https://github.com/UVa-NLP/VMASK/issues/3, https://stackoverflow.com/questions/46433778/import-googlenews-vectors-negative300-bin)
wget -c "https://s3.amazonaws.com/dl4j-distribution/GoogleNews-vectors-negative300.bin.gz"

This downloads the GZIP compressed file that you can uncompress using:
gzip -d GoogleNews-vectors-negative300.bin.gz

You can then use the below command to get wordVector.

from gensim import models
w = models.KeyedVectors.load_word2vec_format('../GoogleNews-vectors-negative300.bin', binary=True)


=======================================================
Part3: evluation metric: SPICE metric issue
Solution:
cd path/coco-caption
./get_stanford_models.sh

Refer to https://github.com/tylin/coco-caption
1) You will first need to download the Stanford CoreNLP 3.6.0 code and models for use by SPICE.
To do this, run: ./get_stanford_models.sh
2) Note: SPICE will try to create a cache of parsed sentences in ./pycocoevalcap/spice/cache/.
This dramatically speeds up repeated evaluations. The cache directory can be moved by setting 'CACHE_DIR' in ./pycocoevalcap/spice. In the same file, caching can be turned off by removing the '-cache' argument to 'spice_cmd'.

ModuleNotFoundError: No module named 'pyemd'
conda install -c conda-forge pyemd

Some solution from other people. But these reasons are not proper for my case.
https://blog.csdn.net/sunny0722/article/details/119946804
https://blog.csdn.net/bit_coders/article/details/120840271
https://github.com/jiasenlu/NeuralBabyTalk/issues/9




投诉或建议