fengyang0317 / unsupervised_captioning

Code for Unsupervised Image Captioning
MIT License
215 stars 51 forks source link

error #26

Open feng-yun-anhui opened 4 years ago

feng-yun-anhui commented 4 years ago

from config import TF_MODELS_PATH ImportError: cannot import name 'TF_MODELS_PATH' from 'config' (D:\python3.7\lib\site-packages\config__init__.py)

what's the mean of TF_MODELS_PATH? I can't find it in config,should I create it by myself? @fengyang0317 can you help me?

fengyang0317 commented 4 years ago

Path to https://github.com/tensorflow/models

feng-yun-anhui commented 4 years ago

I‘m sorry to bother you, can you explain it in more detail? How to use the link you provided ?

feng-yun-anhui commented 4 years ago

link. Failed to open,can you have other ways to download the dataset? Thank you very much.

fengyang0317 commented 4 years ago

链接: https://pan.baidu.com/s/1m-p7aTF0L_mFzPMdKK7btw 提取码: nzqq

feng-yun-anhui commented 4 years ago

$ python preprocessing/crawl_descriptions.py person 1000 0 [] bicycle 1000 0 [] car 1000 0 [] motorbike 1000 0 [] aeroplane 1000 0 [] ... Is this result normal? How to solve it?Looking forward to your reply.

fengyang0317 commented 4 years ago

I will not maintain the crawl_descriptions.py file. You need to change it according to the Shutterstock website.

feng-yun-anhui commented 4 years ago

from config import TF_MODELS_PATH ImportError: cannot import name 'TF_MODELS_PATH' from 'config' (D:\python3.7\lib\site-packages\configinit.py)

what's the mean of TF_MODELS_PATH? I can't find it in config,should I create it by myself? I still haven't solved this problem, can you explain it in more detail.Thank you.

fengyang0317 commented 4 years ago

You should read the code at https://github.com/fengyang0317/unsupervised_captioning/blob/master/config.py

ironmanx1 commented 4 years ago

$ python preprocessing/crawl_descriptions.py person 1000 0 [] bicycle 1000 0 [] car 1000 0 [] motorbike 1000 0 [] aeroplane 1000 0 [] ... Is this result normal? How to solve it?Looking forward to your reply.

sorry to bother you,i also get the same results in this step,but i don't know change which part in crawl_descriptions.py file.Can you help me?thank you~

feng-yun-anhui commented 3 years ago

model_name = 'faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28' path_to_ckpt = (TF_MODELS_PATH + '/research/object_detection/' + model_name

------------------ 原始邮件 ------------------ 发件人: "fengyang0317/unsupervised_captioning" @.>; 发送时间: 2020年8月16日(星期天) 上午6:02 @.>; 抄送: "F @.**@.>; 主题: Re: [fengyang0317/unsupervised_captioning] error (#26)

You should read the code at https://github.com/fengyang0317/unsupervised_captioning/blob/master/config.py

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

fengyang0317 commented 3 years ago

model_name = 'faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28' path_to_ckpt = (TF_MODELS_PATH + '/research/object_detection/' + model_name + '/frozen_inference_graph.pb'tensorflow.python.framework.errors_impl.NotFoundError: /home/fy/PycharmProjects/unsupervised_captioning-master/workspace/tf_models/research/object_detection/faster_rcnn_inception_resnet_v2_atrous_oid_2018_01_28/frozen_inference_graph.pb; No such file or directory how to solve the problem? Looking forward to your reply. ------------------ 原始邮件 ------------------ 发件人: "fengyang0317/unsupervised_captioning" @.>; 发送时间: 2020年8月16日(星期天) 上午6:02 @.>; 抄送: "F @.**@.>; 主题: Re: [fengyang0317/unsupervised_captioning] error (#26) You should read the code at https://github.com/fengyang0317/unsupervised_captioning/blob/master/config.py — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

You need to download the model in https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf1_detection_zoo.md

feng-yun-anhui commented 3 years ago

File "/home/fy/PycharmProjects/unsupervised_captioning-master/im_caption_full.py", line 33, in from nets import inception_v4 File "/home/fy/anaconda3/envs/caption/lib/python3.6/site-packages/slim-0.1-py3.6.egg/nets/inception_v4.py", line 28, in File "/home/fy/anaconda3/envs/caption/lib/python3.6/site-packages/tf_slim-1.1.0-py3.6.egg/tf_slim/init.py", line 25, in from tf_slim.layers import File "/home/fy/anaconda3/envs/caption/lib/python3.6/site-packages/tf_slim-1.1.0-py3.6.egg/tf_slim/layers/init.py", line 25, in from tf_slim.layers.layers import File "/home/fy/anaconda3/envs/caption/lib/python3.6/site-packages/tf_slim-1.1.0-py3.6.egg/tf_slim/layers/layers.py", line 30, in from tf_slim.ops import variables File "/home/fy/anaconda3/envs/caption/lib/python3.6/site-packages/tf_slim-1.1.0-py3.6.egg/tf_slim/ops/variables.py", line 27, in from tensorflow.python.framework import device_spec as tf_device ImportError: cannot import name 'device_spec'

how to solve the problem? Looking forward to your reply.

fengyang0317 commented 3 years ago

The following is a working conda environment. You create a yml file with the following content and then create a conda environment using the yml.

name: caption2
channels:
  - defaults
dependencies:
  - _libgcc_mutex=0.1=main
  - _openmp_mutex=4.5=1_gnu
  - _tflow_select=2.1.0=gpu
  - absl-py=0.11.0=pyhd3eb1b0_1
  - astor=0.8.0=py27_0
  - backports=1.0=pyhd3eb1b0_2
  - backports.shutil_get_terminal_size=1.0.0=pyhd3eb1b0_3
  - backports.weakref=1.0.post1=py_1
  - blas=1.0=mkl
  - c-ares=1.17.1=h27cfd23_0
  - ca-certificates=2021.5.25=h06a4308_1
  - certifi=2020.6.20=pyhd3eb1b0_3
  - cudatoolkit=10.0.130=0
  - cudnn=7.6.5=cuda10.0_0
  - cupti=10.0.130=0
  - decorator=4.4.2=pyhd3eb1b0_0
  - enum34=1.1.6=py27_1
  - funcsigs=1.0.2=py27_0
  - future=0.18.2=py27_0
  - futures=3.3.0=py27_0
  - google-pasta=0.2.0=py_0
  - grpcio=1.27.2=py27hf8bcb03_0
  - h5py=2.9.0=py27h7918eee_0
  - hdf5=1.10.4=hb1b8bf9_0
  - intel-openmp=2021.2.0=h06a4308_610
  - ipython=5.8.0=py27_0
  - ipython_genutils=0.2.0=pyhd3eb1b0_1
  - keras-applications=1.0.8=py_1
  - keras-preprocessing=1.1.0=py_1
  - libffi=3.3=he6710b0_2
  - libgcc-ng=9.3.0=h5101ec6_17
  - libgfortran-ng=7.5.0=ha8ba4b0_17
  - libgfortran4=7.5.0=ha8ba4b0_17
  - libgomp=9.3.0=h5101ec6_17
  - libprotobuf=3.11.2=hd408876_0
  - libstdcxx-ng=9.3.0=hd4cf53a_17
  - linecache2=1.0.0=py_1
  - markdown=3.1.1=py27_0
  - mkl=2020.2=256
  - mkl-service=2.3.0=py27he904b0f_0
  - mkl_fft=1.0.15=py27ha843d7b_0
  - mkl_random=1.1.0=py27hd6b4f25_0
  - mock=2.0.0=py27_0
  - ncurses=6.2=he6710b0_1
  - nltk=3.4.5=py27_0
  - numpy=1.16.6=py27hbc911f0_0
  - numpy-base=1.16.6=py27hde5b4d6_0
  - openssl=1.1.1k=h27cfd23_0
  - opt_einsum=2.3.2=py_0
  - pathlib2=2.3.5=py27_0
  - pbr=5.5.1=py_0
  - pexpect=4.8.0=pyhd3eb1b0_3
  - pickleshare=0.7.5=py27_0
  - pip=19.3.1=py27_0
  - prompt_toolkit=1.0.15=py27_0
  - protobuf=3.11.2=py27he6710b0_0
  - ptyprocess=0.7.0=pyhd3eb1b0_2
  - pygments=2.5.2=py_0
  - python=2.7.18=ha1903f6_2
  - readline=8.1=h27cfd23_0
  - scandir=1.10.0=py27h7b6447c_0
  - scipy=1.2.1=py27h7c811a0_0
  - setuptools=44.0.0=py27_0
  - simplegeneric=0.8.1=py27_2
  - singledispatch=3.6.1=pyhd3eb1b0_1001
  - six=1.16.0=pyhd3eb1b0_0
  - sqlite=3.35.4=hdfb4753_0
  - tensorboard=1.15.0=py27hb230dea_0
  - tensorflow=1.15.0=gpu_py27h0c9f15b_0
  - tensorflow-base=1.15.0=gpu_py27hf473bbb_0
  - tensorflow-estimator=1.15.1=pyh2649769_0
  - tensorflow-gpu=1.15.0=h0d30ee6_0
  - termcolor=1.1.0=py27_1
  - tk=8.6.10=hbc83047_0
  - tqdm=4.59.0=pyhd3eb1b0_1
  - traceback2=1.4.0=py27_0
  - traitlets=4.3.3=py27_0
  - unittest2=1.1.0=py27_0
  - wcwidth=0.2.5=py_0
  - webencodings=0.5.1=py27_1
  - werkzeug=0.16.1=py_0
  - wheel=0.36.2=pyhd3eb1b0_0
  - wrapt=1.11.2=py27h7b6447c_0
  - zlib=1.2.11=h7b6447c_3
  - pip:
    - cloudpickle==1.1.1
    - dm-tree==0.1.5
    - gast==0.2.2
    - tensorflow-gan==1.0.0.dev0
    - tensorflow-probability==0.8.0
    - tf-slim==1.1.0
prefix: /opt/anaconda3/envs/caption2
feng-yun-anhui commented 3 years ago

https://github.com/tensorflow/models/tree/master/research/gan https://github.com/tensorflow/models/tree/master/research/maskgan https://github.com/tensorflow/models/tree/master/official/resnet The above three links cannot be opened,can you have other ways to download? Thank you very much.

fengyang0317 commented 3 years ago

Replace master with archive https://github.com/tensorflow/models/tree/archive