Download the critical dataset update and apply it.Copy the contents of the directory Release_Code_v1_1_beta\HumanEva_I to the root of the source tree ( Release_Code_v1_1_beta/).Download the official source code v1.1 beta and extract it where you extracted the dataset.Download the HumanEva-I dataset and extract it.We provide a MATLAB script to extract the revelant parts of the dataset automatically. Python prepare_data_2d_h36m_sh.py -ft stacked_hourglass_fined_tuned_įor HumanEva, you need the original dataset and MATLAB. Python prepare_data_2d_h36m_sh.py -pt h36m.zip You can download these directly and put them in the data directory. For reference, our best results on Human3.6M are achieved by cpn_ft_h36m_dbb. You only need to download the detections you want to use. The other detections must be downloaded manually (see instructions below). Ground-truth poses ( gt) have already been extracted by the previous step. Since all the files are encoded according to the same format, it is trivial to create a custom set of 2D detections. h36m) and DETECTION is the 2D detection source (e.g. The 2D detection source is specified through the -keypoints parameter, which loads the file data_2d_DATASET_DETECTION.npz from the data directory, where DATASET is the dataset name (e.g.
0 Comments
Leave a Reply. |