Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
O
ocr-fusion
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
schaper
ocr-fusion
Repository graph
Repository graph
You can move around the graph by using the arrow keys.
master
Select Git revision
Branches
1
master
default
protected
1 result
Begin with the selected commit
Created with Raphaël 2.2.0
30
Sep
21
11
10
31
Aug
27
25
Upload previously missing requirements.txt
master
master
Fix small style issue
Add cold fusion model and clean up of general structure as well as clean up of comments
Add project report pdf
Add pre-trained checkpoints for the two models that can be loaded in ocr_fusion.ipynb
Add the two final runs of the models' training so so that the loss curves and CER/WER plots on the validation set can be viewed via tensorboard
Add sections on purpose, directory structure, usage, requirements and results
Add inference functionality
Add csv file creation, data loading and training loop
Add .csv files that correctly transcribe the respective images of the respective data split
Testing .gitignore
Add structure for preprocessing of images from dataset such that they all have the same size (as mandated by ResNet)
Remove moved files from dataset
Add .ipynb checkpoint files
Update .txt with file extensions as means to sort into train, val and test data
Reorganize files to test, train and validation sets (val_1 and val_2)
Add initial jupyter notebook and add char-based LM with logit output
Add initial data for evaluation
Add .gitignore so that macOS folder file is ignored
Add LICENSE
Initial commit
Loading