deep-high-resolution-net.pytorch

deep-high-resolution-net.pytorch copied to clipboard

Segmentation fault (core dumped) after main() returned in tools/test.py

3

I am currently running the following sample script on a Ubuntu 18.04.4 LTS AMD Ryzen 3920x machine with 24 physical cores and 3 GPUs, all detected by pytorch: `python3 tools/test.py...

WaiTsun-Yeung

测试时，当yaml 中USE_GT_BBOX为false时，`lib/dataset/coco.py ` 中 136行 `gt_db = self._load_coco_person_detection_results()`，_load_coco_person_detection_results 函数里只读取了 bbox，没有读取关键点，请问是否是代码bug？ 

SherlockUnknowEn

train my own dataset , but AP is very low

10

Recently I run HRnet keypoint detection code, I didn't use any PRETRAINED MODEL (including ImageNet and COCO datasets), then train and test（use groundtruth bbox） my own datasets(My own dataset is...

ing-NT

I am looking at the code of class `JointsDataset`, `COCODataset`, `MPIIDataset`. Is there any documentation about the code?

shizidushu

AssertionError: Invalid device id

8

chappie1998

Ignoring Invisible keypoints at inference time.

1

I am running demo.py and making inference on testing videos. But the invisible keypoints locations are not that accurate. So, I want to ignore that keypoints and get only visible...

myatthukyaw-edu

How I can use this network on custom datasets?

1

Hi, I am wondering how to use this architecture on a custom dataset. Plus when test where the results are saved and how to visualize the results? Thanks

khandriod

Demo

45

First of all thank you for the great work. I'm currently trying to set up a demo of the estimator but run into some issues in the post-processing stage (the...

MassyMeniche

coco数据集输入数据是原图去训练还是输入标注部分人体ROI区域进入网络训练？

2

哈喽，在coco数据上训练姿态的时候代码是输入的coco的原图去训练还是输入标注部分人体ROI区域进入网络训练的，代码在那部分有实现，我看代码感觉输入整图加单人的姿态点。这样每张图的其他人的图片信息会不会对训练产生干扰信息？

APeiZou

HRNet-Human-Pose-Estimation/tools/../lib/nms/gpu_nms.cpython-36m-x86_64-linux-gnu.so: undefined symbol: __cudaRegisterFatBinaryEnd 有人遇到过同样的问题吗？

APeiZou