Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
M
Machine Learning
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
Terms and privacy
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
johannes bilk
Machine Learning
Graph
4124ea3f3a6132d298eed305267b944ff383bec2
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
17
Apr
5
22
Mar
20
15
14
13
12
8
7
6
5
7
Sep
6
5
30
Aug
29
17
15
14
11
10
7
5
1
31
Jul
29
28
27
26
25
24
22
Mar
Update file README.md
main
main
migration to github
fuck git, use jujutsu
reverted back to trees without datasets... this is way fast. also I reverted back by hand, because git is not very userfriendly
models will be zipped now to save space. dataloader can do bootstraping now. a lot of code will need rewriting.
there's still A LOT of work in quantization
continued work on quantization
added a layer that automatically quantizes data
quantization works... technically
asdf
more on PTQ, struggling with activation functions
still working towards PTQ
added quantization to read me
updated quantization code... not fully working yet.
proof of concept of PTQ
weights quantization can be saved/loaded
preparations for PTQ
outlier detection using forrests
clean up
continiued OD preparation
fixes/preparation for OD trees
dataset integration into decision trees
deleted an old json file
fixed an error in the network test file
fixed an error in convolution parameter check. added json files for models for jupyter notebooks
added some doc strings, added ‘indent’ to modelIO class
added baking to forrests
trees can be baked now… it’s not elegant, but it works for now
added some file handling stuff to modelIO
reverted back to generators in decision trees, speed up wasn’t as great and it was less readable
updated smaller things in decision trees
replaced generators with lambda functions to speed up training/learning in decision trees
Merge branch 'master' into 'main'
updated some decision tree code
updated leaf functions
Merge branch 'master' into 'main'
forrest test
updated multi processing/threading of decision trees.
fixed an import issue in __init__ for nn
Add LICENSE
Loading