human-pose-estimation.pytorch
human-pose-estimation.pytorch copied to clipboard
microsoft
The project is an official implement of our ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking(https://arxiv.org/abs/1804.06208)"
Hi, I recently try to re-implement the flow-based propagation section in your paper. I use the FlowNet2S you mentioned, and I get the flow information between two adjacent frames on...
@leoxiaobin Hi, when I was training along with validation under my own dataset, when do validation occurs this kind of errors: AssertionError: Results do not correspond to current coco set...
Hi, I am trying to perform inference by using the pre-trained model (resnet150_coco). Need help on the following: 1. I am not able to map key-points to the original body...
I would like to ask you if your proposed smiple baselines network is top-down or bottom-up. I think it should be top-down. I don't know if my understanding is correct....
Hi, Is there a way to disable cudnn for batch norm on pytorch 1.0?
this is not an issue but rather an observation. What i did: - use ground truth box in json as input instance box - disable flip test - disable oks_nms...
@leoxiaobin Hi, I've found that you exchanged the stride size of conv1 and conv2 in the first Bottleneck of layer2, layer3, layer4, just to make sure with you(since, a paper...
Thanks for your excellent works! I have a question about the result you show in the Fig3. in the paper "Simple Baselines for Human Pose Estimation and Tracking." In the...
I can't run the code on windows and I also can't install Linux right now due to personal issues, I am currently just backtracking everything in your code right now...
I want like to evaluate the accuracy of the pretrained model with a subset of images of MPII (let's call these images subset A). I have the annotations of subset...
