mmpose

mmpose copied to clipboard

为什么所有Bottom_up模型的config文件中的输入图片大小都是宽高相同的？

6

例如在`res50_crowdpose_512x512.py`中： ``` 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=False, ) ``` 如果我想让输入图片size变为[512, 384]，应该怎么设置参数？

calmiLovesAI

Using ONNX model for inference

5

Hi! Is it possible to use ONNX model to inference? Model have a heatmap output and I don't know how to integrate it for inference using mmpose post processing functions...

soltkreig

Does mmpose support the evaluation of human pose tracking（MOT）? I didn't find the relevant configuration file

6

I want to evaluate the tracking effect after using the filter

kongyan66

Any ONNX model exported method of litehrnet or some demo related？

5

hi， 请问下，是否有litehrnet的demo，以及相关导出为onnx模型的例子？ 具体是哪个版本里面会有？ 我只看到了hrnet，但是必须litehrnet才行。多谢 BR

2050airobert

We are building Chinese Documentation now. PRs of translation from the community are welcomed. To make the community fully aware of the progress, we list here the documents to translate....

ly015

How to resume from latest checkpoint automatically?

4

How to resume from latest checkpoint automatically during training?

WeianMao

Integration of state of the art pose estimation: ViTPose.

3

Hi awesome developers from MMPose. A new state of the art pose estimation research has published their code. https://github.com/ViTAE-Transformer/ViTPose MMPose is the leading open-source project in this field, so I...

khanhha

MixSTE (3D human pose estimation method on video) is preparing to support MMPose

1

Hi, just a mark. I am rebuilding the code of MixSTE (https://arxiv.org/abs/2203.00859) to support the MMPose, the training on the MPII dataset has been finished, and the training on H36M...

JinluZhang1126

Multi-Instance Pose Networks (MIPNet)

2

Hi! Firstly, thank you for this wonderful library. May I know if there are any plans to implement [MIPNet](https://github.com/rawalkhirodkar/MIPNet) in mmpose? It is particularly useful to tackle data where there...

levan92

Run_webcam.py中发现一个bug

4

使用自己训练的hrnet_w32 config+checkpoint来检测airplane的关键点，运行过程中发现无法检测到airplane目标，会出现airplane标签位于左上角但未出现bbox框的情况。而使用之前训练的hrnet_w48+checkpoint未发现这样的状况。。

ShaneCan