res-loglikelihood-regression
res-loglikelihood-regression copied to clipboard
Jeff-sjtu
Code for "Human Pose Regression with Residual Log-likelihood Estimation", ICCV 2021 Oral
Hi Jeff， I downloaded h36m dataset from the official website. Based on your dataset structure, there are supposed to be some sub directories for h36m data, e.g, "s_01_act_02_subact_01_ca_03". But no...
Dear author， I have 2 questions for you, 1. What's the purpose of following calculation: img[0].add_(-0.406) img[1].add_(-0.457) img[2].add_(-0.480) 2. Have you ever succeeded in converting pth to onnx format? Thanks...
Hi, I'm interested in RLE. it is a nice job. I notice that you embed RLE into two-stage 3D HPE methods, such as SRnet, but I didn't see it in...
great work! i wonder why coords and lables multiply hm_widt(hm_height/hm_depth) ?and Isn't this a regression method, Why is there a heatmap?
1. Why design a separate linear layer for the output of the coordinate mean, and what is the difference between it and the ordinary fully connected layer? 2. 3. Why...
Thanks for your great work! May I ask if you have adopted this method in Hybrik?
Dear jeffe，the figure 4 in your paper shows some distribution details， but i don't konw how to plot it ， could you give some help？
Hi there, It seems the bar_mu computation is different. Should be multiplying a "-1". (below Eqn (5), bar_mu = (gt - mu_pred) / sigma. As shown here: https://github.com/Jeff-sjtu/res-loglikelihood-regression/blob/203dc3195ee5a11ed6f47c066ffdb83247511359/rlepose/models/regression_nf.py#L134 This does...
Hi ,i see some experiment of training on mpii dataset but in your code,i can't find about it so i want to ask how to do it
thanks for author The outputs in coco have AP AP.5 AP.75 ...... but in your code's outputs only have mAP So i want to ask how to get Ap.5 .........