Skip to content

Rebase from main #124

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
georgeyiasemis merged 2 commits into from
Oct 17, 2021
Merged

Rebase from main #124

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2d2f323
Update README.md
georgeyiasemis Oct 12, 2021
961989b
Update README.md
georgeyiasemis Oct 12, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions projects/calgary_campinas/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,23 +3,23 @@ This folder contains the training code specific for the [Calgary Campinas challe
As of writing (25 Oct 2020) this is the top result in both Track 1 and Track 2.

## Training
The standard training script `train_rim.py` in [tools/](tools) can be used. If you want, the validation volumes can be computed using `predict_val.py`.
The standard training script `train_model.py` in [tools/](tools) can be used. If you want, the validation volumes can be computed using `predict_val.py`.
During training, validation metrics will be logged, these match the challenge metrics.
For our submission we used [base.yaml](configs/base.yaml) as model configuration.

After downloading the data to `<data_root>` a command such as the one below was used (running in the docker container, which maps the code to `direct`):
After downloading the data to `<data_root>` a command such as the one below was used to train a RIM (running in the docker container, which maps the code to `direct`):
```
cd /direct/tools
python train_rim.py <data_root>/Train/ \
python train_model.py <data_root>/Train/ \
<data_root>/Val/ \
<output_folder> \
--name base \
--cfg /direct/projects/calgary_campinas/configs/base.yaml \
--cfg /direct/projects/calgary_campinas/configs/base_rim.yaml \
--num-gpus 4 \
--num-workers 8 \
--resume
```
Additional options can be found using `python train_rim.py --help`.
Additional options can be found using `python train_model.py --help`.


## Prediction
Expand Down