mxnet_Realtime_Multi-Person_Pose_Estimation icon indicating copy to clipboard operation
mxnet_Realtime_Multi-Person_Pose_Estimation copied to clipboard

This is a mxnet version of Realtime_Multi-Person_Pose_Estimation, origin code is here https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation

Results 18 mxnet_Realtime_Multi-Person_Pose_Estimation issues
Sort by recently updated
recently updated
newest added

Hard to reproduce the result mentioned in Cao's original paper, they talk about it in the original implementation. https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation/issues/35 https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation/issues/68 https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation/issues/72 https://github.com/ZheC/Realtime_Multi-Person_Pose_Estimation/issues/74 The matlab version should be 0.577 Python I...

@dragonfly90 I'm trying to test a model that I trained myself. I've changed the `output_prefix` to `"testConfigModel"`. However, I get this error in this line in `testModel.ipynb`: ```python cmodel =...

Hi, I try to use mxnet model which is given in comments by a c++ interface. I don't understand how the results is formatted at the output of chain and...

Hi @dragonfly90 evaluation_coco.py evaluate only for origin coco model. do you have source code to evaluate new model (after pretrain)? Thank you

I have several problems for your porject. 1.could you share model files in other way,google drive coulen't be open at all; 2.when i run demo .I got error: No module...

i implement the heatmap and paf generate as operators. https://github.com/li-haoran/mxnet-cmu_pose, and implement some image data augmentations method. and train with different lr_mult. now noly on the MPII, and the train...

Table 4 in papar mentioned that CPM refinement can provide more than 2-point AP increase. Is it a post-processing method? Has it been added to this existed code?

layer { name: "image" type: "Slice" bottom: "data" top: "image" top: "center_map" slice_param { slice_point: 3 axis: 1 } } layer { name: "silence2" type: "Silence" bottom: "center_map" } @dragonfly90...

Hi @dragonfly90 , can you please explain how your data.json is organized? Cause I'd like to finetune this model to a new dataset where there are 14 keypoints to be...

@dragonfly90 thanks for your share~ I'm try to modify it to fit AI challenge keypoint detection. Now i found a problem about load_checkpoint and save_checkpoint function. such as https://github.com/dragonfly90/mxnet_Realtime_Multi-Person_Pose_Estimation/blob/master/TrainWeight.py#L89 For...