Commit History

Message Author SHA1 Date
reformatting the training file   Dean 1 week ago
update with Colab Badge   Dean 2 weeks ago
Merge branch 'simplifying-savta-depth' of OperationSavta/SavtaDepth into pipeline-setup   Dean 1 month ago
Merge branch 'pipeline-setup' into simplifying-savta-depth   Dean 1 month ago
Update '.dvc/config'   Dean 1 month ago
Update 'README.md'   Dean 2 months ago
Added a simplified version of the colab notebook, which doesnt have a clean env setup. This simplifies the setup process greatly at the cost of hurting reproducibility. Further research into ways to get a clean env on colab is required   Dean 2 months ago
train model on colab after fixing normalization bug   dean 2 months ago
remove secondary requirements (i.e. not things that are explicitly installed by the user), fix normalization problem, and use tqdm for image processing progress bar   Dean 2 months ago
Add hosted storage remote and make it default   Dean 2 months ago
Update 'README.md'   Dean 2 months ago
Merge branch 'pipeline-setup' of https://dagshub.com/OperationSavta/SavtaDepth into pipeline-setup   Dean 2 months ago
Fixing colab after feedback   Dean 2 months ago
Update 'README.md'   Dean 2 months ago
Update 'README.md'   Dean 2 months ago
Update readme to include google colab setup + remove problematic packages from requirements.txt   Dean 2 months ago
adding more setup options to readme   Dean 2 months ago
removed problematic requirements   Dean 3 months ago
Added dvc pull instruction as dvc checkout only works locally.   Dean 3 months ago
Added escaping slash to run_dev_env.sh so that it works in windows as well   Dean 3 months ago
Successfully configured the dataloader and trained for one epoch. Results are not so good, but it's something. Still the Fastaiv1 looked better qualitatively   Dean 4 months ago
Finished training of model, saving before qualitative testing. Seems model has actually learned something. Need to add metrics and params to the pipeline.   Dean 4 months ago
Fixed a bug in the training stage where the model was not saved, commiting before training on colab   Dean 4 months ago
Training stage seems to work, creating a non-run commit to use colab as an orchestration machine   Dean 4 months ago
Seems like we are now using the correct format for fastai2. Still there is a strange bug where the signal is killed in training   Dean 4 months ago
Merge branch 'split_commands_in_readme' of OperationSavta/SavtaDepth into pipeline-setup   Dean 4 months ago
*Split commands of preparing environment in README file > *added -y for conda env creation for less interactions for the user   Gal Braun 4 months ago
Migrated to fastai2, creating the DataLoader now works but I'm stuck on not being able to change the batch_size or num_workers as the interface seems to have changed   Dean 4 months ago
Hopefully finished with the requirements debacle, now using conda but freezing requirements with pip as usual   Dean 5 months ago
Fixed requirements.txt to comply with conda format   Dean 5 months ago