Spaces:

kingabzpro
/

savtadepth

Paused

6 contributors

Dean

Successfully configured the dataloader and trained for one epoch. Results are not so good, but it's something. Still the Fastaiv1 looked better qualitatively

13f0309 over 4 years ago

.dvc
Hopefully finished with the requirements debacle, now using conda but freezing requirements with pip as usual over 4 years ago
Notebooks
Transition to MLWorkspace docker and setup makefile with environment commands over 4 years ago
src
Successfully configured the dataloader and trained for one epoch. Results are not so good, but it's something. Still the Fastaiv1 looked better qualitatively over 4 years ago
.dvcignore

139 Bytes

Finished data import and processing setup, bug in training step over 4 years ago
.gitignore

93 Bytes

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 over 4 years ago
Makefile

1.43 kB

*Split commands of preparing environment in README file > *added -y for conda env creation for less interactions for the user over 4 years ago
README.md

3.33 kB

*Split commands of preparing environment in README file > *added -y for conda env creation for less interactions for the user over 4 years ago
dvc.lock

769 Bytes

Successfully configured the dataloader and trained for one epoch. Results are not so good, but it's something. Still the Fastaiv1 looked better qualitatively over 4 years ago
dvc.yaml

461 Bytes

Fixed a bug in the training stage where the model was not saved, commiting before training on colab over 4 years ago
requirements.txt

1.84 kB

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 over 4 years ago
run_dev_env.sh

227 Bytes

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 over 4 years ago