CMU Preprocessed Dataset

Samleo8 / learnable-triangulation-pytorch

The repository that this is forked from is an official PyTorch implementation of the paper "Learnable Triangulation of Human Pose" (ICCV 2019, oral). Proposed method archives state-of-the-art results in multi-view 3D human pose estimation! This repo aims to extend the capabilites to the CMU dataset

MIT License

27 stars 11 forks source link

CMU Preprocessed Dataset #6

Open anas-zafar opened 1 year ago

anas-zafar commented 1 year ago

Great work @Samleo8 ! Is it possible of you could share the preprocessed data of the cmu panoptic dataset? Thanks

anas-zafar commented 1 year ago

@Samleo8 I am having this issue while trying to generate labels for the cmu dataset. Could you please guide me how to resolve this? Thanks Traceback (most recent call last): File "generate-labels-npy.py", line 421, in retval['table'] = np.concatenate(retval['table']) File "<__array_function__ internals>", line 6, in concatenate ValueError: need at least one array to concatenate

fxyQAQ commented 1 year ago

Hello, have you solved the problem? How did you use detectron2 to pre-process the video?