APeiZou

python tools/test.py \ --cfg experiments/coco/hrnet/w32_256x192_adam_lr1e-3.yaml \ TEST.MODEL_FILE models/pytorch/pose_coco/pose_hrnet_w32_256x192.pth \ TEST.USE_GT_BBOX False python tools/test.py \ --cfg experiments/coco/hrnet/w32_256x192_adam_lr1e-3.yaml \ TEST.MODEL_FILE models/pytorch/pose_coco/pose_hrnet_w32_256x192.pth \ TEST.USE_GT_BBOX True

pose_hrnet_w48* means using additional data from AI challenger for training？有 AI challenger 和coco数据集合并完成的数据集提供吗？

1

pose_hrnet_w48* means using additional data from AI challenger for training？有 AI challenger 和coco数据集合并完成的数据集提供吗？@HuangJunJie2017

How to perform quantitative compression on your own model？？？？？？

for catId in catIds} File "/home/sa/anaconda3/envs/torch1.7/lib/python3.6/site-packages/pycocotools/cocoeval.py", line 229, in computeOks e = (dx**2 + dy**2) / vars / (gt['area']+np.spacing(1)) / 2 ValueError: operands could not be broadcast together with shapes (294,) (17,)

1

训练的时候出现以下错误 for catId in catIds} File "/home/sa/anaconda3/envs/torch1.7/lib/python3.6/site-packages/pycocotools/cocoeval.py", line 229, in computeOks e = (dx**2 + dy**2) / vars / (gt['area']+np.spacing(1)) / 2 ValueError: operands could not be broadcast together with...

How to get the 10 body shape information and 24 hand movement information of smpl-x model?

1

@chingswy Hello， how to get the 10 body shape information and 24 hand movement information of smpl-x model?

@chingswy It is a great work. How is the idea of the whole pipeline realized? Is there any documentation about the implementation of the whole pipeline? Optimize global RT，and how...

@qqlu 哈喽，您好,CropFormer训练代码有实现吗？是用的mask2former的代码吗？

@HuangJunJie2017 您好，可以在UDP的heatmap的基础上运用simcc的方法吗？

@XavierXiao Hello， is there any method for loop t-step denoising to restore images and parallel speed up in stable diffusion？

@Annbless @seaman1900 @AK391 hello, which config file can train COCO+AIC+MPII dataset？this config file vitPose+_huge_coco+aic+mpii+ap10k+apt36k+wholebody_256x192_udp.py can train all of the data