mmpose
mmpose copied to clipboard
open-mmlab
OpenMMLab Pose Estimation Toolbox and Benchmark.
## Motivation Integrate single depth to 3D hand keypoints into mmpose. ## Modification Add an algorithm for estimating 3D gestures from a single depth image to mmpose Includes the following...
想对MAP,AP,AR,GFLOPS等性能进行测试，但是发现在训练过程中的测试环节，出现下列状况： [>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>] 37/37, 0.7 task/s, elapsed: 54s, ETA: 0sLoading and preparing results... 2022-07-03 11:12:43,314 - mmpose - INFO - Epoch(val) [10][2] AP: 0.0000, AP .5: 0.0000, AP .75: 0.0000, AP...
Excited for your great work! I am a rookie for mmpose and I would like to train a top-down multi-head model for the keypoint prediction and the keypoints radiance regression,...
## Motivation DeciWatch is a simple baseline framework for video-based 2D/3D human pose estimation that can achieve 10× efficiency improvement over existing works without any performance degradation. paper: https://arxiv.org/pdf/2203.08713.pdf website:...
According to the model architecture, the videopose3d_1frame model should be able to do image 2d to 3d lift inference. But when I try, I got the error ``` File "demo/body3d_two_stage_img_demo.py",...
Hi folks, I used MMPose to train on CarFusion dataset using HRNet with UDP implemented ([hrnet_w32_coco_384x288_udp](https://github.com/open-mmlab/mmpose/blob/master/configs/body/2d_kpt_sview_rgb_img/topdown_heatmap/coco/hrnet_w32_coco_384x288_udp.py)). The error `ValueError: cannot convert float NaN to integer` happened as I passed the...
How to export the model to torchscript？
这是我在配置文件中设置的： ``` data_cfg = dict( image_size=256, base_size=128, base_sigma=2, heatmap_size=[64, 128], num_joints=channel_cfg['dataset_joints'], dataset_channel=channel_cfg['dataset_channel'], inference_channel=channel_cfg['inference_channel'], num_scales=2, scale_aware_sigma=False, ) ``` 我知道这里的base_size是用作multi scale test的，但是我在test_cfg里的设置是`scale_factor=[1]`，也就是说只有一个缩放比例，就是它本身，但是我在测试过程中打印了data_loader，修改代码如下： ``` def single_gpu_test(model, data_loader): """Test model with a single gpu....
I have tried running the demo file for the multiview 3D keypoints detection using voxel pose, but could only see the predicted keypoints as visualizations on the images. Is there...
Hi, I would like to try pre-trained Voxelpose with my own data. However, I did not understand which parameters will be written in camera_parameters.json file. tests/data/panoptic_body3d/demo/camera_parameters.json doesn't exist, therefore I...
Metadata
Owner
Metadata
OpenMMLab Pose Estimation Toolbox and Benchmark.