mmpose icon indicating copy to clipboard operation
mmpose copied to clipboard

OpenMMLab Pose Estimation Toolbox and Benchmark.

Results 432 mmpose issues
Sort by recently updated
recently updated
newest added

Hello I have several questions : 1 : what is the latest version 0 or 1 ? and is the version 2 which will arrive in January improve a lot...

hi, 1 The occlusion keypoints (vis = 1) in the coco-wholebody dataset have participated in the training , right ? 2 If I want to exclude the occlusion keypoints (vis...

info/1.x

Sorry to bother you again. I tried to use mmdeploy to convert the trained model and it was successfully converted to the model in tensorrt format. Could you please tell...

![image](https://user-images.githubusercontent.com/52156532/204189097-88eb8f22-9ebf-4c47-aea2-529134658eed.png) I need to run webcam_demo.py on jetson nano, so I need the lightest object detection model, please help me to see which of the following models is the lightest

Hi, Question 1: more quesetion added ,if I want to my training running on the gpu 2 not 1, how should I do with the following training cmd? Question 2:...

info/1.x

I wonder if anyone has encountered a similar problem when using a single-resolution pred map to consulate mseloss , there will report that tensors size mismatch between preds and gt....

info/1.x

Hello ,I would like to ask how to use mmdeploy to transfomer my own backbone(mobilevit) to do inference,and what is the difference from onnxruntime、tensorrt、pplnn、ncnn

I tried to run the demo on the Jetson Nano using the GPU. I set CUDA_VISIBLE_DEVICES=0, but found that the GPU did not work after running

Hello! I try to run the training demo with cmd ``` python tools/train.py configs/body_2d_keypoint/topdown_regression/coco/td-reg_res50_rle-8xb64-210e_coco-256x192.py ``` Unfortunately, I got the error as follows ``` 11/21 14:32:31 - mmengine - INFO -...

info/1.x

Hello! I have a question about mode inferencing. I want to use the model pretrained by mmpose in other projects. I wonder if it is possible for me to directly...