brandonhanx / fame-vil Goto Github PK
View Code? Open in Web Editor NEW[CVPR 2023 (Highlight)] FAME-ViL: Multi-Tasking V+L Model for Heterogeneous Fashion Tasks
License: Other
[CVPR 2023 (Highlight)] FAME-ViL: Multi-Tasking V+L Model for Heterogeneous Fashion Tasks
License: Other
Hello!
I got this error when installing omegaconf== 2.1 !
raise ConfigKeyError(f"Missing key {key}")
omegaconf.errors.ConfigAttributeError: Missing key config
full_key: config
object_type=dict
Any idea how to fix this error?
Thanks
Did you use the test protocol of original val with 3,817, 6,346 and 5,373 images or the protocol of the paper Image Search With
Text Feedback by Visiolinguistic Attention Learning which is the union of the reference and target images with
redundancy removed? Such two protocols may produce large difference of recall score
I have an error when running the requirements.txt (build dependencies etc), which version of python do you use ?
Thank you for your excellent work. I noticed that only the test dataset was mentioned in the paper. I would like to know which datasets were used during the training phase.
Hello and thanks for your amazing work,
do you know how it compares to Fashion-Clip(https://github.com/patrickjohncyh/fashion-clip)?
Greetings
Hey,
great work! :)
Could you provide a minimal example for loading the given pretrained fashionclip model and get the embedding for an example image?
Thanks in advance,
Marco
hello, this is a good job.
When update detailed Readme?
Thanks
Could you please update the readme to show us how to test and train for XMR task ,also SCR and FIC.
I am not sure how you perform the test but I can't get the result as shown in your paper
Thank you very much
This is an awesome work, could you please provide me some guidance about how to use this model for Fashion Image Captioning?
THX a lot❤
Hi,
Thank you for your work,
I wonder what are the missing keys for fashionIQ dataset?
the original dataset doesn't have 'fake_data' , 'target_id' and 'garment_class' values.
Also for fashionGen dataset and dataloader as it is implemented in "mmf/datasets/builders/fashionall/database.py' , the original dataset keys (h5 file) doesn't contain these keys ("image_path", "id", "sentences", "attributes_id", etc).
I can't evaluate and reproduce results without these .
Is there any script for preparing datasets or
something like that?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 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. 📊📈🎉
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 ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.