huangying
huangying
If you are on linux. first you should clone the code. Then `cd ~/ccv/lib` Run ./configure And then run make,this will create the ccv.a lib Things will done here.
some detail can be found here https://github.com/liuliu/ccv/issues/131
Unclear instruction on how to apply this framework to a new dataset. (e.g. get 2d / 3d pseudo poses)
can you give a detail expression about how to train and evaluate this model on my own dataset. The readme for pseudo_2d_labels_generation is not clear for me.
Unclear instruction on how to apply this framework to a new dataset. (e.g. get 2d / 3d pseudo poses)
Thank you for your reply. When I followed the step in pseudo_2d_labels_generation, the s1 generate image_info_train_panoptic.json from a TRAIN_DB_PATH, I want to know how can I generate the TRAIN_DB_PATH for...
Unclear instruction on how to apply this framework to a new dataset. (e.g. get 2d / 3d pseudo poses)
Thanks for your reply. When I generate TRAIN_DB_PATH from lib/dataset/_get_db, I found the dataset read a pickle file group_train_cam5_pseudo_hrnet_hard_9videos.pkl for panoptic and pred_campus_maskrcnn_hrnet_coco.pkl for campus dataset. How can I generate...