Update README.md

BenjaminFiltjens · Jan 24, 2022 · 1767778 · 1767778
1 parent 70d44f0
commit 1767778
Showing 1 changed file with 6 additions and 2 deletions.
diff --git a/README.md b/README.md
@@ -1,5  1,4 @@
 # Multi-Stage Spatial-Temporal Convolutional Neural Network (MS-GCN)
-
 This code implements the skeleton-based action segmentation MS-GCN model from [Automated freezing of gait assessment with
 marker-based motion capture and multi-stage
 spatial-temporal graph convolutional neural
@@ -8,7  7,6 @@ networks](https://arxiv.org/abs/2103.15449) and [Skeleton-based action segmentat
 It was originally developed for freezing of gait (FOG) assessment on a [proprietary dataset](https://movementdisorders.onlinelibrary.wiley.com/doi/10.1002/mds.23327). Recently, we have also achieved high skeleton-based action segmentation performance on public datasets, e.g. [HuGaDB](https://arxiv.org/abs/1705.08506), [LARa](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7436169/), [PKU-MMD v2](https://arxiv.org/abs/1703.07475), [TUG](https://www.nature.com/articles/s41597-020-00627-7).
 
 ## Requirements
-
 Tested on Ubuntu 16.04 and Pytorch 1.10.1. Models were trained on a
 [Nvidia Tesla K80](https://www.nvidia.com/en-gb/data-center/tesla-k80/).
 
@@ -34,6  32,12 @@ After processing the dataset (scripts are dataset specific), each processed data
 
 Please refer to the example in `data/example/` for more information on how to structure the files for training/prediction.
 
 ## Pre-trained models
 Pre-trained models are provided for HuGaDB, PKU-MMD, and LARa. To reproduce the results from the paper:
 * See the "Data" section for more information on how to prepare the datasets;
 * Place the pre-trained models in `models/, e.g. `models/hugadb;
 * Run label_eval with proper arguments, e.g. `--dataset=hugadb.
 
 ## Acknowledgements
 The MS-GCN model and code are heavily based on [ST-GCN](https://github.com/yysijie/st-gcn) and [MS-TCN](https://github.com/yabufarha/ms-tcn). We thank the authors for publicly releasing their code.