tkim-snu / glacnet Goto Github PK
View Code? Open in Web Editor NEWGLAC Net: GLocal Attention Cascading Network for the Visual Storytelling Challenge
Home Page: http://www.visionandlanguage.net
License: MIT License
GLAC Net: GLocal Attention Cascading Network for the Visual Storytelling Challenge
Home Page: http://www.visionandlanguage.net
License: MIT License
How do I test your project on a set of random images using the pretrained models? Say, I have a folder that has 5 images and I need to generate text for them, is that possible?
I have a similar SIS JSON file but doesn't contain storylet_id in annotations.
I would like to know the exact role of that line in the GLACNet/data_loader.py file as it seems like it was just defined and not used for anything.
Is it possible for me to use your code without that line??
I am trying to run the project with the pre-trained model. I followed all the steps mentioned in the Prerequisites and evaluation part. I downloaded the SIS file and the pre-trained models from the provided link and placed .pkl files in the models folder: encoder-0.pkl, decoder.pkl, vocab.pkl.
I am getting the below error message. I tried with both versions of Python 2.7 and 3.6
ubuntu@ip-xxx-xx-xx-xxx:~/GLACNet**$ python3.6 eval.py --model_num 0**
Traceback (most recent call last):
File "eval.py", line 81, in
vocab = pickle.load(f)
_pickle.UnpicklingError: invalid load key, '<'.
My system configuration:
GPU: 1 , vCPUs: 4
CUDA: V10.0.130, Python: 3.6
Can you please help me if I am missing anything or doing something wrong..
Thank you
Can you please share the number of epochs that you trained the model for, and what were the values of the other parameters to obtain the pretrained model that you have currently provided? After which epoch did the model start overfitting and what were the corresponding loss values?
I am unable to get the files in the data folder and files in models folder.
Hi,
I tried to run the build_vocab.py. It seems like I do not have the following file. Could you explain a little bit of the sis file? or where could I obtain it? Did I miss something?
Traceback (most recent call last):
File "build_vocab.py", line 79, in <module>
main(args)
File "build_vocab.py", line 61, in main
threshold=args.threshold)
File "build_vocab.py", line 28, in build_vocab
vist = VIST(sis_file, )
File "/data/chacha/GLACNet/vist.py", line 6, in __init__
sis_dataset = json.load(open(sis_file, 'r'))
FileNotFoundError: [Errno 2] No such file or directory: './data/sis/train.story-in-sequence.json'
Thank you so much.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.