APeiZou

Is there a tutorial for the self-supervised learning method mentioned in the code repository?

1

Hello @ifzhang Is there a tutorial for the self-supervised learning method mentioned in the code repository?

./yolov5: error while loading shared libraries: libcudnn.so.8: cannot open shared object file: No such file or directory

3

## Env - GPU, P40 - OS, Ubuntu18.04 - Cuda 10.2 - TensorRT 7.2.3.4 ## About this repo - master branch - yolov5 ## Your problem - what is your...

Why is the number of categories for training coco 2 instead of 81?

4

Hello,@WXinlong Why is the number of categories for training coco 2 instead of 81?

Hi，@thohemp 

Why do I need to load 2D data when training 3D data？

13

 Why do I need to load 2D MPII dataset when training the 3D Human36M dataset？

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？

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？

Hello, all. Is there any tool to convert torch's HRnet model to tf-lite model?

hello, all有开发将torch的HRnet模型转换为tf-lite模型的工具吗？

what's wrong with this ? everybody kowns, help!!!!!! AssertionError: COCOAPI does not support empty polygons

2

[04/20 12:23:58 d2.utils.events]: eta: 2:29:30 iter: 19 total_loss: 3.171 loss_ins: 2.299 loss_cate: 0.9552 time: 0.1545 data_time: 0.0114 lr: 9.9905e-06 max_mem: 1153M [04/20 12:24:01 d2.utils.events]: eta: 2:31:05 iter: 39 total_loss: 2.703...