search

bmartacho / UniPose

We propose UniPose, a unified framework for human pose estimation, based on our “Waterfall” Atrous Spatial Pooling architecture, that achieves state-of-art-results on several pose estimation metrics. Current pose estimation methods utilizing standard CNN architectures heavily rely on statistical postprocessing or predefined anchor poses for joint localization. UniPose incorporates contextual seg- mentation and joint localization to estimate the human pose in a single stage, with high accuracy, without relying on statistical postprocessing methods. The Waterfall module in UniPose leverages the efficiency of progressive filter- ing in the cascade architecture, while maintaining multi- scale fields-of-view comparable to spatial pyramid config- urations. Additionally, our method is extended to UniPose- LSTM for multi-frame processing and achieves state-of-the- art results for temporal pose estimation in Video. Our re- sults on multiple datasets demonstrate that UniPose, with a ResNet backbone and Waterfall module, is a robust and efficient architecture for pose estimation obtaining state-of- the-art results in single person pose detection for both sin- gle images and videos.
Other
211 stars 44 forks source link

Where is waspnet defined? I'd like to use the pre-trained weights but am not able to define the model architecture #38

Closed mukeshnarendran7 closed 2 years ago

mukeshnarendran7 commented 2 years ago

NameError Traceback (most recent call last)

in () 58 59 if name == "main": ---> 60 model = waspnet(backbone='resnet', output_stride=16) 61 model.eval() 62 input = torch.rand(1, 3, 513, 513)

NameError: name 'waspnet' is not defined

A-qingtongxiaoyou commented 1 year ago

Hi, i have the same bug as you. Could you tell me how to debug? Thanks!

mukeshnarendran7 commented 1 year ago

Whats your mail id. I can share the notebook i used with you if you like. I was able to load the weights and all but you can test it further if you like

A-qingtongxiaoyou commented 1 year ago

@.*** Thank you very much for your reply！ 

彭畅 @.***

 

------------------ 原始邮件 ------------------ 发件人: "bmartacho/UniPose" @.>; 发送时间: 2022年10月7日(星期五) 下午4:05 @.>; @.**@.>; 主题: Re: [bmartacho/UniPose] Where is waspnet defined? I'd like to use the pre-trained weights but am not able to define the model architecture (Issue #38)

Whats your mail id. I can share the notebook i used with you if you like. I was able to load the weights and all but eventually I did not end up using it

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.***>

A-qingtongxiaoyou commented 1 year ago

ctchang@mail.scut.edu.cn Thank you very much for your reply！

mukeshnarendran7 commented 1 year ago

Sent it.

bring-nirachornkul commented 1 year ago

I have this problem too. My e-mail is blinkdrive555@gmail.com

IsraaSamkari commented 1 year ago

Could you send me the whole code? I am facing many problems in fixing the code. My e-mail is IsraaSamkari@hotmail.com