sunbo11112

这个代码太难训练了，2025年全新架构，欢迎交流泛化384 576 768，欢迎加V交流 Mxcz2019zz

泛化384 576 768，欢迎加V交流 Mxcz2019zz

have a higher definition private dataset with approximately 10000 people and facial resolutions of 384 or higher. We can collaborate on training together. Please contact me, wx：Mxcz2019zz Completely private shooting...

The saved training model is pth, while resume_from_checkpoint: True ， How to solve the problem of loading bin?

3

The saved training model is pth, while resume_from_checkpoint: True ， How to solve the problem of loading bin?

Loads checkpoint by local backend from path: ./models/dwpose/dw-ll_ucoco_384.pth Segmentation fault (core dumped)

1

Loads checkpoint by local backend from path: ./models/dwpose/dw-ll_ucoco_384.pth Segmentation fault (core dumped) I am here On the autodl H20 NVLink * 1 card, following the documentation to install the environment,...

The data processing is very slow, so we cannot update a faster script

4