LearnTrajDep
LearnTrajDep copied to clipboard
code for learning trajectory dependencies for human motion prediction
Hi, I try to run the code of LTD (Learning Trajectory Dependencies for Human Motion Prediction Wei) and get the same result as you released in your paper and github...
Hello, I am looking into the joints that were ignored for the Humans 3.6m skeletons when dealing with 3D coordinates instead of angles. It is mentioned in the source code...
When I try to run demo.py use pretrained model `model_path_len = './checkpoint/pretrained/h36m_in10_out25_dctn35.pth.tar'` and I got a peoblem as follow: ` Traceback (most recent call last): File "G:\2021 summary\Graduation project\LearnTrajDep-master\demo.py", line...
Hi. May I ask how you preprocess the original human 3.6 dataset to get the exponential map? Thanks a lot!
Hello, when I try to run : `python main.py --epoch 5 --input_n 10 --output 10 --dct_n 20 --data_dir home/h3.6m/dataset/` I get to the training: >>> data loaded ! >>> train...
Hello, I am trying to use 3D coordinates with Conv Seq2Seq model. My output freezes up as seen in the GIF.  Could you please provide code that you used...
Could you please share the hyperparameter values you used for the different input and output sequence lengths? Particularly for the Human 3.6M dataset.
在上一个问题中解决了内存溢出问题,但是我在运行demo.py文件时,只有第一张照片能正常显示,其余都是空白,请问如何解决呢? 
After multiple calls to loss_func.mpjpe_error and loss_func.euler_error, GPU memory is fully occupied. This may be due to some variables not being released properly.