Abolfazl kaviani

Hi @bearpaw thanks in advance, what does scaling mean in coco I would appreciate your comment for following link https://github.com/bearpaw/pytorch-pose/blob/0867835dc33c3740774b4b4e235d6339af3b9f9e/miscs/cocoScale.m#L1

pretrained model

1

Hi @jricheimer Thank you so much for your implementation, It would be great if we can get access to pretrained model to compare it's accuracy with paper. Thanks,

Memory used by Warping

2

Hi @hassony2 , Thanks for sharing the code, I have treid second stage of training; meshwarp; after some epochs, for me 50 epochs, occupied memory goes around 128 G, I...

Tracking Code

1

Hi , Thanks for your great paper, I am also interested in your tracking code, How can we access to that? Thanks,

Hi @anewell , Thanks for your paper, I have seen the paper results total accuracy `PCKH @0.5 ` as `90.9` but when I compute the accuracy from prediction you provide...

Hi @iqbalu , Itried to compile caffe to rrun your code , but I got following error, can I ask cuda and cuddn version to use your code? `src/caffe/layers/cudnn_tanh_layer.cu(13): error:...

Hi @spurra , Thank you in advance, in regard with figure 6, have you just walk on one dimension of start latent vector or you interpolate on all dimension of...

Hi, I have trained your network for first `sub-JHMDB` according to it's default settings, but it 's results on test set is lower than result s of provided weights as...

Hi, Have you changed the image pre-processing of `CPM` for `video` dataset? Would you please share the trained `CPM` weights on `video` dataset for further comparison. Thanks,

> We reproduce the evaluation protocol initially introduced in [68] by training on 10 sequences and testing on the remaining 2 and aligning predictions to the ground-truth hand root joint...