formerlya
formerlya
me too…
When I use pose.Keypoints[0].ID, it worked. But except nose(0) and neck(17), how to judge them if they exist and get their value. such as left_knee ……
Thank you very much for your answer, I am a novice, thank you for your advice!
The file generated by tensorrt can't work for deepstream? But, I see version 5.1 deepstream tutorial can realize, 6.0 series can't? jetson+yolov5+tenssort+deepstream6.0's imformation is too little to learn, pure beginner....
May I ask if you can directly test with the weights you provide? The accuracy of the test in pointmamba is only 7%~8%, and the weight files provided by them...
并且当我训练的时候 会nan 同样的数据，在mae中可以正常训练 请问可以直接使用代码中的超参数吗，需要针对性调整？
> > 并且当我训练的时候 会nan 同样的数据，在mae中可以正常训练 请问可以直接使用代码中的超参数吗，需要针对性调整？ > > I'm sorry, we never encountered an issue with NaN. Thank you very much for your answer~
torch 1.13.1+cu117 torchvision 0.14.1+cu117 python 3.9
when I test with python eval_diffusion.py --config "allweather.yml" --resume 'WeatherDiff64.pth.tar' --test_set 'rainfog' --sampling_timesteps 25 --grid_r 16 the input image is 1 * 3 * 480 * 720 the xt_patch and...