HyperPose
HyperPose copied to clipboard
Library for Fast and Flexible Human Pose Estimation
Someone can answer that for me in the [hyperpose/dataset/mpii_dataset/Dataset/mpii_dataset/generate.py](https://github.com/tensorlayer/hyperpose/blob/master/hyperpose/Dataset/mpii_dataset/generate.py) ``` target_list=[] for kpts,head_bbx in zip(kpts_list,bbx_list): bbx=np.array(head_bbx).copy() bbx[:,2]=bbx[:,2]*4 bbx[:,3]=bbx[:,3]*4 target_list.append({ "kpt":kpts, "mask":None, "bbx":bbx, "head_bbx":head_bbx, "labeled":1 }) ``` What does **bbx[:,2]=bbx[:,2]\*4** and...
Hi, I am unable to find the file newest_model.npz for Resnet50 backbone architecture. Is the pretrained models released? If so where can i find the .npz file? If not, when...
Loss is Nan in training based on [openpose] + [VGG19] after 6800 iterations nan in training based on [openpose] + [Resnet18] after 74300 iterations, as blow: Train iteration 74300 /...
Hi @ganler. Thanks for your awesome work. I use your openpose coco 368x656 tensorrt model to get human pose. I am very happy when i tested tried your hyperpose `openpose...
Hello guys, great job with this project! Thanks. I notice that you released only one pretrained (.npz) model corresponding to the lightweight-openpose in this [link](https://drive.google.com/drive/folders/1kFbl7c7DUN19o7Qca3GpcNUjOHjNaCcO). Do you plan to release...
When building with ``` cmake .. \ -DCMAKE_BUILD_TYPE=Release \ -DBUILD_EXAMPLES=OFF \ -DBUILD_TESTS=OFF \ -DBUILD_PACKAGE=ON \ -DBUILD_CLI=OFF \ -DBUILD_USER_CODES=OFF cmake --build . ``` I get the following output / error: ```...
Hello! Thanks for the amazing work !! I would like to know if the hyperpose supports BODY25 model. I've gone through the support section, but haven't found any details related...
Hi, I publish a research conference paper on monkey pose estimation that makes use of this repo. I am in the process of making the paper public at https://www.biorxiv.org/ In...
I looked at several questions to try to use it in Win, but I didn't see if it was successful in Win, so I wanted to ask if it was...
hyperpose-master/hyperpose/Model/openpose/train.py:224 one_step * pd_conf,pd_paf,stage_confs,stage_pafs=train_model.forward(image,is_train=True) anaconda3/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py:457 __call__ result = self._call(*args, **kwds) hyperpose-master/hyperpose/Model/openpose/model/openpose.py:57 forward * init_conf,init_paf=self.init_stage.forward(backbone_features) hyperpose-master/hyperpose/Model/openpose/model/openpose.py:135 forward * conf_map=self.conf_block.forward(x) anaconda3/lib/python3.7/site-packages/tensorlayer/layers/core.py:673 forward * z = layer.forward(z) anaconda3/lib/python3.7/site-packages/tensorlayer/layers/activation.py:99 forward * neg = -self.alpha_var_constrained...