mmpose

mmpose copied to clipboard

run camera_demo on MCU

1

I am running the demo on a Jetson Nano and I was wondering if there is any way to speed it up and increase the frame count

ChenZhenGui

td-hm_hrnet-w32_coco doubt?

2

Hello! I found that dev1.0 has changed a lot, but I have doubts about the pose output, what does its output mean, and its post-processing code is encapsulated. Where is...

chen-del

camera_demo

3

When I'm ready to run the camera_demo,I dont need the animal pose, How should I set the parameters

ChenZhenGui

TypeError: Unsupported format: data\pigBehavior\vis_results

3

I'm running "python tools\test.py configs\pig\pig_behavior.py work_dirs\pig_behavior\best_PCK_epoch_80.pth --out data\pigBehavior\vis_results "When testing, he reported this error 

hsp2454

webcam_demo.py

4

I used my trained model to run the camera demo. When no one was detected, everything was normal. When someone was detected, the error was as follows  I tried...

ChenZhenGui

something about videopose3D

3

Is the data used in the training of videopose3d pre-trained by preprocessing_h36m.py?

Ared521

tests folder should exclude from the installation

2

Thanks for your error report and we appreciate it a lot. If you feel we have helped you, give us a STAR! :satisfied: **Checklist** 1. I have searched related issues...

hubutui

When I use my own dataset，the loss is 0

10

Reimplement a custom model but all the components are implemented in MMPose. My picture‘s information like this：  Used the config like this:  but the loss is 0 ...

zhzh1234

Question about preprocess_h36m.py

4

When running preprocess_h36m.py, after extracting s1-s11, I reported the following problems: File "preprocess_h36m.py", line 141, in generate_annotations = self._load_annotations( File "preprocess_h36m.py", line 308, in _load_annotations with pycdf.CDF( File "D:\Software\Anaconda\envs\mmPose\lib\site-packages\spacepy\pycdf\__init__.py", line...

Ared521

Reimplementation results about integral pose regression

2

I am using the following command with 4 RTX 2080Ti: NNODES=1 NODE_RANK=0 PORT=29501 MASTER_ADDR="127.0.0.1" CUDA_VISIBLE_DEVICES=0,1,2,3 bash tools/dist_train.sh configs/body_2d_keypoint/integral_regression/coco/ipr_res50_8xb64-210e_coco-256x256.py 4 --work-dir work_dirs/ipr_res50_8xb64-210e_coco-256x256 --cfg-options train_dataloader.batch_size=8 train_dataloader.num_workers=2 but final results drop about 5%...

ducongju