Run evaluation on MuPoTS dataset with estimated 2D joints as input
Evaluation instructions to reproduce the results (PCK and PCK_abs) are provided in the next section. The following table is similar to Table 3 in the main paper, where the quantitative evaluations on MuPoTS-3D dataset are provided (best performance in bold). This tool keeps a track of all your times and display them. Simply press the Space Bar again to stop it. Hold the Space Bar and release it whenever youre ready to launch the timer. Usage MuPoTS dataset evaluation 3D Multi-Person Pose Estimation Evaluation on MuPoTS Dataset See how much of a speedcuber you are With this application, you can easily time all of your cube solvings.
|- other python code, LICENSE, and README files |- mupots <- the downloaded processed human keypoint files Inside the training tab you'll see a list for speed scrambles, OLL practice, PLL practice, and LL practice. This tool is ideal for any situation where you need to track points and make the scoreboard available to other people online. The basic version is free and requires no user account. Create your own scoreboard or leaderboard for up to 350 players and start tracking points. |- MultiPersonTestSet <- the newly added MuPoTS eval set ZYX timer doesn't do a lot of things very unique, but it does have a couple notable features such as the training tab which no other timer features. KeepTheScore is an online software for scorekeeping. |- ckpts <- the downloaded pre-trained Models Now you should see the following directory structure. Unzip it and move the folder MultiPersonTestSet to the root directory of the project to perform evaluation on MuPoTS test set. After the download is complete, a MultiPersonTestSet.zip is avaiable, ~5.6 GB. You need to download the mupots-3d-eval.zip file, unzip it, and run get_mupots-3d.sh to download the dataset. MuPoTS eval set is needed to perform evaluation as the results reported in Table 3 in the main paper, which is available on the MuPoTS dataset website.
Models and Testing Data Pre-trained Modelsĭownload the pre-trained model and processed human keypoint files here, and unzip the downloaded zip file to this project's root directory, two folders are expected to see after doing that (i.e.
Install dependencies pip install - r requirements.txtīuild the Fast Gaussian Map tool: cd lib/fastgaus For example, command to use on Linux with CUDA 11.0 is like: conda install pytorch torchvision cudatoolkit=11.0 -c pytorch
Install the latest version of pytorch (tested on pytorch 1.5 - 1.7) based on your OS and GPU driver installed following install pytorch.