AntoineH/smart_augmentation
1
0
Fork 0
mirror of https://github.com/AntoineHX/smart_augmentation.git synced 2025-05-04 04:00:46 +02:00
Code Issues Projects Releases Packages Wiki Activity

Update readme

Browse source
This commit is contained in:
Harle, Antoine (Contracteur) 2020-01-30 11:16:22 -05:00
parent 5cd50ca9f3
commit 6bba069d8a
1 changed files with 5 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

8
README.md
View file

@ -13,10 +13,10 @@ It's also possible to use the, non-differentiable, data augmentation module 'Ran
* Python version >= 3.5 * Python version >= 3.5
* PyTorch version >= 1.3 * PyTorch version >= 1.3
* Kornia version >= 0.2.0 * Kornia version >= 0.2.0
* Higher version >= * Higher version >= 0.1.5
* Optionnal: * Optionnal:
..* matplot >= ..* matplot >= 3.1.1
## Kornia ## Kornia
@ -101,4 +101,6 @@ We rely on the 'Higher' library to solve this bi-level optimisation problem. See
## Code example ## Code example
An example use of Smart_aug can be found in 'test_dataug.py' with Augmented model, and 'run_dist_dataugV3' in 'train_utils.py'. An example use of Smart_aug can be found in 'smart_aug_example.py', and 'run_simple_smartaug' in 'train_utils.py'.
For more control over the optimization process see 'test_dataug.py' and 'run_dist_dataugV3' in 'train_utils.py'.