Extracting pose estimates from detected objects

WongKinYiu / yolor

implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)

GNU General Public License v3.0

1.98k stars 524 forks source link

Extracting pose estimates from detected objects #224

Open Aishkrish18 opened 2 years ago

Aishkrish18 commented 2 years ago

Hello @WongKinYiu , I am interested to try this algorithm and extract the estimated poses of the objects along with object detection as implicit knowledge. I am quite new to implementing this and I would like to know if this is possible and if this would require ensemble learning to extract poses separately. Any other steps or suggestions in this regard would be really appreciated!

Thanks Aishwarya

yxx-byte commented 2 years ago

Excuse me, can you analyze the weight file of yolov4 CSP? I want to make a comparative analysis. thank you.