Khanh Ha

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...

the reason behind the usage of render_onehot_heatmap for training target instead of render_gaussian_heatmap

3

Hi, I would like to ask about the difference between the two kinds of heatmaps in two repositories from you. - In the PoseFix repo, I noticed that you used...

input image normalization

4

Hello, sorry for asking you too many questions. I would like to know where the input images are actually normalized to ImageNet mean and standard deviation? As far as I...

stackwalker decoder fails to decode minidump file generated by crashpad_handler

6

hi, thanks for building a wonderful app. we are having an issue with using your server to decode a minidump file generated by crashpad_handler. we tested the symbols and minidump...

failed fp16 inference.

4

hi, I have modifed your export function for fp16 infernece. I run into the following issue. Here is the modfied export code ``` pmodel.load_state_dict(ckpt) pmodel.eval() pmodel.cuda() pmodel.half() C, H, W...