mmpose
mmpose copied to clipboard
open-mmlab
OpenMMLab Pose Estimation Toolbox and Benchmark.
In the det_checkpoint file top_down_img_demo_with_mmdet.py, if I want to train my own data, then in addition to training the attitude estimation model, I also need to train a target detection...
its in the picture is defined in the for loop. May I ask if it cannot be output after the for loop?
In config, we can set `scale_aware_sigma` to True to use dynamic sigma, like below: ``` data_cfg = dict( image_size=512, base_size=256, base_sigma=2, heatmap_size=[128], num_joints=channel_cfg['dataset_joints'], dataset_channel=channel_cfg['dataset_channel'], inference_channel=channel_cfg['inference_channel'], num_scales=1, scale_aware_sigma=True, ) ``` in...
I was able to train a model using mmpose on cooc tiny following the tutorial and run predict and inference. But how may I evaluate my new model and report...
Do I need to frame the body when labeling data with labelme? How to convert a json file to coco format
Hello, I am very interested in the work of RLE. So when I found out that mmpose implements RLE Loss, I was also very excited. However, when I compared the...
我使用的程序是tool/test.py,算法是voxelpose，我输入的campus类型的（2000*3个摄像头图片），我想得到程序推理出来的2000张融合的照片，我该怎么做？我应该用tool/test.py来推理吗？
I want to input videos from multiple perspectives (such as three videos) into the algorithm"[3D human pose](https://github.com/open-mmlab/mmpose/blob/master/demo/docs/3d_human_pose_demo.md) "to get a 3D result. What should I do?
Hi, 请问下 1 hrnet 训练的时候，采用了哪些数据增广呢？是否有针对不同的物体或者人 检测框box 尺寸和大小随机调整的数据增广呢？ 具体文档链接是？ 2 就是说假如前面输入的人检测出来的box 比人要大的多而且尺寸 宽高比也很异常，那么这种情况的数据增广是怎么处理的呢？ 具体代码体现在哪个地方呢？ 具体代码位置是？ BR
Metadata
Owner
Metadata
OpenMMLab Pose Estimation Toolbox and Benchmark.