Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
L
LiT4RSVQA
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Package Registry
Container Registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Issue analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Terms and privacy
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
RSiM
LiT4RSVQA
Graph
571d15ccda7656b632fc1b752c69a1822c00a16e
Select Git revision
Branches
1
main
default
protected
1 result
You can move around the graph by using the arrow keys.
Begin with the selected commit
Created with Raphaël 2.2.0
27
Oct
9
Jun
1
22
May
17
16
15
11
10
3
26
Apr
Updating README with reference from IEEE
main
main
added arxiv link to readme
preparing for release
preparing for release
changing monitor to use correct metric in checkpointing
adding precision to matmul op for torch>1.12
changing to hparams from chappuis
Changing MUTAN rank to 10 instead of 1
switching from precision in trainer to matmul precision in torch
amp flag seems to have been invalid
adding mixed precision to rsvqa-t
Changing the lr to be default correct
changing default values for epochs and val epochs
removing flop count that does not work
adding flop analysis
tokenizer were not provided in dataloader, now they are
removing force mock
adding vision pretraining tag automatically on train start
Adding TransformerRSVQA code and update to configilm v0.3.0 to make code runable
adding training script and gitingore
adding dl worker param
init with env-v1 and pretraining script
Loading