lizz
lizz
@ioctl-user Please checkout the new modelzoo! * By topic: https://mmpose.readthedocs.io/en/latest/topics/animal.html * By paper: https://mmpose.readthedocs.io/en/latest/papers/algorithms.html
> one loads up the entire dataset into system ram this is not the case
@zengwang430521 The implementation could be improved.
Please try the image demo with mmdet, to see if it can process images one by one. https://github.com/open-mmlab/mmpose/blob/master/demo/2d_human_pose_demo.md#using-mmdet-for-human-bounding-box-detection
I have no experience in jetson xavier :( My uneducated guess is that its a pytorch+nvidia thing. Could you succesfully train/inference a classification model, such as resnet18 on it?
Again I have no experience in Jetson. We can try to isolate the error. 1. See if demo in mmdet runs https://github.com/open-mmlab/mmdetection/tree/master/demo . If it runs successfully, then its a...
@lweingart Thanks for your additional input. From the stacktrace, it is the nms op that cannot run. So my bet is that ops in mmcv was not compiled successfully. To...
Do you have ideas on code improvement, or could you please give more details on the problem?
It seems that there are oppertunity to speed up.
Could you please describe which algorithm, which config, and ideally which example image you are interested in?