Skip to content
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

docs: bit misspell in README and comments #16

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

docs: bit misspell in README and comments #16

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b1fa830
docs: bit misspell one comment
guspan-tanadi Sep 12, 2023
43d21e6
docs: bit misspell in comments
guspan-tanadi Sep 12, 2023
b3f461a
docs: bit misspell in README
guspan-tanadi Sep 12, 2023
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
4 changes: 2 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@

<p align="center"> <img src='imgs/teaser.jpg' align="center" > </p>

## Enviroment Setup
## Environment Setup
All our experiments are done on a single V-100 16G GPU.
```
conda env create -f environment.yml
Expand Down Expand Up @@ -80,7 +80,7 @@ python train.py --save_dir /path/to/save/your/model --dataset amass --weight_dec
## Pretrained Weights
The pretrained weights for AGRoL can be downloaded from this link: https://github.com/facebookresearch/AGRoL/releases/tag/v0

To download the wights automatically, please run `bash prepare_data/download_model.sh`.
To download the weights automatically, please run `bash prepare_data/download_model.sh`.

To test the pretrained AGRoL diffusion-model:
```
Expand Down
4 changes: 2 additions & 2 deletions data_loaders/dataloader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -141,10 +141,10 @@ def load_data(dataset, dataset_path, split, **kwargs):
split : train or test
input_motion_length : the input motion length

Outout:
Output:
- For test:
filename_list : List of all filenames in the dataset
motion_list : List contains N dictoinaries, with
motion_list : List contains N dictionaries, with
"hmd_position_global_full_gt_list" - sparse features of the 3 joints
"local_joint_parameters_gt_list" - body parameters Nx7[tx,ty,tz,rx,ry,rz] as the input of the human kinematic model
"head_global_trans_list" - Tx4x4 matrix which contains the global rotation and global translation of the head movement
Expand Down
6 changes: 3 additions & 3 deletions test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -336,7 +336,7 @@ def evaluate_prediction(
filename,
):
motion_pred = sample.squeeze().cuda()
# Get the prediction from the model
# Get the prediction from the model
model_rot_input = (
utils_transform.sixd2aa(motion_pred.reshape(-1, 6).detach())
.reshape(motion_pred.shape[0], -1)
Expand All @@ -354,7 +354,7 @@ def evaluate_prediction(
}
).Jtr

# Get the offset in global coordiante system between head and body_world.
# Get the offset in global coordinate system between head and body_world.
t_head2root = -body_pose_local[:, 15, :]
t_root2world = t_head2root + t_head2world.cuda()

Expand All @@ -374,7 +374,7 @@ def evaluate_prediction(
body_param[k] = v.squeeze().cuda()
body_param[k] = body_param[k][-predicted_angle.shape[0] :, ...]

# Get the ground truth position from the model
# Get the ground truth position from the model
gt_body = body_model(body_param)
gt_position = gt_body.Jtr[:, :22, :]

Expand Down