search

zychen423 / KE-VIST

The code and output of our AAAI paper "Knowledge-Enriched Visual Storytelling"
GNU General Public License v3.0
40 stars 9 forks source link

Problem in stage 1 #4

Closed FeatherZhong closed 3 years ago

FeatherZhong commented 3 years ago

Thank you for sharing the code, I am trying to reproduce the result of the paper, but I have a problem in the first stage. In the instructions you mentioned using faster RCNN to extract object feature, and I saw you mentioned this repository in another issue. So I tried to extract the features using the lib folder in the repository and the code you provided in stage 1 and I got the error message because your code is python3 but in lib it's python2. Can you tell me the details of how to extract features using faster RCNN? Thanks!

joe32140 commented 3 years ago

Hi, Thank you for your interest in our paper!

Could you provide more details about the error message you got?

FeatherZhong commented 3 years ago

Thank you for your prompt reply, The errors I get look like running a python2 code using python3 Traceback (most recent call last): File "/home/jiangaiwen/KE-VIST/src/stage1/image_object_detection/tools/generate_tsv.py", line 15, in <module> from fast_rcnn.test import im_detect,_get_blobs File "/home/jiangaiwen/KE-VIST/src/stage1/image_object_detection/tools/../lib/fast_rcnn/test.py", line 222 print filename ^ SyntaxError: Missing parentheses in call to 'print'. Did you mean print(filename)?

The error was in this code fast_rcnn/test.py

joe32140 commented 3 years ago

Did remove parentheses from test.py help? or did just run with python2 work? I might have tried the former. I don't have access to the code base now. I will redirect you to my co-author! He may help me to push the code here.

FeatherZhong commented 3 years ago

Yes, I've tried to transfer the code in lib to python3, but there's so much to change that I don't think it's the right way to do it. I saw in the README that you're using python3.6, and I have not tried to change your code to run python2, because I configured pycaffe to run python3, and configuring Caffe can be a real hassle.If you do use python2 to extract data. I'll try it next.

FeatherZhong commented 3 years ago

I solved this problem by runnning on python3 and fixing every python2 errors, after finally configuring Caffe for my Python environment, I successfully ran code to extract image features. Thank you very much for your help!

xinli2008 commented 3 years ago

Hi,I have came across the same problems,can you share the Modified code？ And can i have you email for further discussion? @FeatherZhong