Disk usage warning: after preprocessing, the total sizes of datasets are around 77G, 157GB, 63GB for NTU RGB+D 60, NTU RGB+D 120, and Kinetics 400, respectively. The raw/intermediate sizes may be larger.
There are 3 datasets to download:
Request dataset here: http://rose1.ntu.edu.sg/Datasets/actionRecognition.asp
Download the skeleton-only datasets:
nturgbd_skeletons_s001_to_s017.zip
(NTU RGB+D 60)nturgbd_skeletons_s018_to_s032.zip
(NTU RGB+D 120, on top of NTU RGB+D 60)Download missing skeletons lookup files from the authors' GitHub repo:
NTU RGB+D 60 Missing Skeletons:
wget https://raw.githubusercontent.com/shahroudy/NTURGB-D/master/Matlab/NTU_RGBD_samples_with_missing_skeletons.txt
NTU RGB+D 120 Missing Skeletons:
wget https://raw.githubusercontent.com/shahroudy/NTURGB-D/master/Matlab/NTU_RGBD120_samples_with_missing_skeletons.txt
Remember to remove the first few lines of text in these files!
Download dataset from here
Move all_sqe
to ./data/NW-UCLA
Put downloaded data into the following directory structure:
- data/
- nturgbd_raw/
- nturgb+d_skeletons/ # from `nturgbd_skeletons_s001_to_s017.zip`
...
- nturgb+d_skeletons120/ # from `nturgbd_skeletons_s001_to_s017.zip``nturgbd_skeletons_s018_to_s032.zip`
...
- NTU_RGBD_samples_with_missing_skeletons.txt
- NTU_RGBD120_samples_with_missing_skeletons.txt
Download pretrained models for producing the final results on NTU RGB+D 60, NTU RGB+D 120, NW-ucla:
Put the folder of pretrained models at repo root:
- multi-stream/
- pretrained-models/
- main.py
- ...
bash eval_pretrained.sh
The general training template command:
python3 main.py
--config <config file>
--work-dir <place to keep things (weights, checkpoints, logs)>
The general testing template command:
python3 main.py
--config <config file>
--work-dir <place to keep things>
--weights <path to model weights>
Template for stream fusion:
python3 ensemble.py
--dataset <val_label path> \
--one <work_dir of your test command for frame-level joint model> \
--two <work_dir of your test command for frame-level bone model> \
--three <work_dir of your test command for sequence-level joint model> \
--four <work_dir of your test command for sequence-level bone model> \
Use the corresponding config files from ./config
to train/test different datasets
This repo is based on
Thanks to the original authors for their work!