Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
iamap
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
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
AMAP
iamap
Graph
ceba7025b05a92d92fc6f28b863a930b89f15ddc
Select Git revision
Branches
5
dev
default
protected
ga-windows
install-issues
main
pg
5 results
You can move around the graph by using the arrow keys.
Begin with the selected commit
Created with Raphaël 2.2.0
16
Apr
15
14
11
10
9
8
7
3
2
1
31
Mar
27
25
21
19
18
17
12
10
7
4
28
Feb
21
17
31
Jan
10
5
Dec
3
2
25
Nov
21
20
19
14
8
28
Oct
25
24
23
22
21
18
17
8
7
4
3
2
30
Sep
27
26
17
6
5
4
3
2
30
Aug
show install pop up if install is not done, avoid to be soft lock behind "dont' show again message". should end #50
install-issues
install-issues
split dependency check and pop up show into two stages, show pop up only if not settings 'dont_show_pop_up' is not set
add checkbox
ignore pretrained_models dir
change torch install and cuda version handling. Should solve #49
commit to save several tests
pg
pg
generalisation of vit_first_layer_nchans for any model with a conv2d as first layer
helper function to get the first layer of any model
reorder adavanced params in docs
reorder adavanced params more logically and typo
comment previous exxplaination
detail encoding parameters in doc
detail encoding parameters in doc (not finished)
init pretrained weights with n channels modulo the number of input channels in the original model rather than an hardcoded 3
reorder features dimensions
first draft with single model. Features are outputed in the wrong shape for now (c inverted with w probably ?)
explore configs
add util to manually change ViT input layers
add description paragraph
dev main
dev main
rename tools section tutorial and remove tutorial section
change section name and remove bamboo example for now
working feature extraction
fix mamba args
ga-windows
ga-windows
fix mamba args
fix mamba args
test with mamba
rename branch in ga
tests ga on windows
instantiate model via pangaea
add configs
forking https://github.com/VMarsocci/pangaea-bench/ encoders
cleanup comment, test push on several urls
update link in notes
update issue page name
update headers
improve video embeding
rm search at the top
Update examples.md
Update examples.md
complete roadmap for future developments
Loading