Skip to content

Update tutorial notebooks to use WOD 1.3.0 configs #92

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

Open
Vedant-Mhatre wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update tutorial notebooks to use WOD 1.3.0 configs #92

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 3 additions & 3 deletions docs/notebooks/data_demo.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,9 +38,9 @@
},
"source": [
"\n",
"We first create a dataset config, using the default configs provided in the `waymax.config` module. In particular, `config.WOD_1_1_0_TRAINING` is a pre-defined configuration that points to version 1.1.0 of the Waymo Open Dataset.\n",
"We first create a dataset config, using the default configs provided in the `waymax.config` module. In particular, `config.WOD_1_3_0_TRAINING` is a pre-defined configuration that points to version 1.3.0 of the Waymo Open Dataset.\n",
"\n",
"The data config contains a number of options to configure how and where the dataset is loaded from. By default, the `WOD_1_1_0_TRAINING` loads up to 128 objects (e.g. vehicles, pedestrians) per scenario. Here, we can save memory and compute by loading only the first 32 objects stored in the scenario.\n",
"The data config contains a number of options to configure how and where the dataset is loaded from. By default, the `WOD_1_3_0_TRAINING` loads up to 128 objects (e.g. vehicles, pedestrians) per scenario. Here, we can save memory and compute by loading only the first 32 objects stored in the scenario.\n",
"\n",
"We use the `dataloader.simulator_state_generator` function to create an iterator\n",
"through Open Motion Dataset scenarios. Calling next on the iterator will retrieve the first scenario in the dataset.\n"
Expand All @@ -54,7 +54,7 @@
},
"outputs": [],
"source": [
"config = dataclasses.replace(_config.WOD_1_1_0_TRAINING, max_num_objects=32)\n",
"config = dataclasses.replace(_config.WOD_1_3_0_TRAINING, max_num_objects=32)\n",
"data_iter = dataloader.simulator_state_generator(config=config)\n",
"scenario = next(data_iter)"
]
Expand Down
2 changes: 1 addition & 1 deletion docs/notebooks/multi_actors_demo.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@
"max_num_objects = 32\n",
"\n",
"config = dataclasses.replace(\n",
" _config.WOD_1_0_0_VALIDATION, max_num_objects=max_num_objects\n",
" _config.WOD_1_3_0_VALIDATION, max_num_objects=max_num_objects\n",
")\n",
"data_iter = dataloader.simulator_state_generator(config=config)\n",
"scenario = next(data_iter)"
Expand Down