ST-GCN 使用+复现
- 下载所需数据集 Kinetics 与 NTU-RGB+D
Kinetics(百度云)下载地址
NTU-RGB+D (their website) (Only the 3D skeletons(5.8GB) modality is required in our experiments)
stgcn官方使用了Kinetics-skeleton和NTU RGB+D两个数据集来进行训练,我们要将自己的训练集先转换为这两个数据集的格式然后再转化为stgcn的格式,或者直接转化为stgcn的格式.
After uncompressing, rebuild the database by this command:
python tools/kinetics_gendata.py --data_path <path to kinetics-skeleton>
After that, this command should be used to build the database for training or evaluation:
python tools/ntu_gendata.py --data_path <path to nturgbd+d_skeletons>
where the <path to n