microsoft
What's the correspondence of joints in Posetrack format to those in COCO format?
In your paper, you used pretrained model on COCO and then fine-tuned on Posetrack. But their points format are different, so there must be a conversion otherwise the model could not be used. How did you convert COCO format to Posetrack 17 in your experiment?
I am also interested in evaluating the model on posetrack data.
@nikhilaravi
Actually I removed the last layer of author-provided COCO model. I added random initialized layer and the output size = 15. I trained this on posetrack 17 training set.
I am also interested in evaluating the model on posetrack data.
@nikhilaravi
Actually I removed the last layer of author-provided COCO model. I added random initialized layer and the output size = 15. I trained this on posetrack 17 training set.
Hello，what’ s your model peformance? And can you share your code about your operation mentioned above? Thanks!
I am also interested in evaluating the model on posetrack data.
@nikhilaravi Actually I removed the last layer of author-provided COCO model. I added random initialized layer and the output size = 15. I trained this on posetrack 17 training set.
Hello，what’ s your model peformance? And can you share your code about your operation mentioned above? Thanks!
Sure. Reply to me if you still want it and I will add some comments. It reached 69.6 mAP on Posetrack 2017 validation set.
I am also interested in evaluating the model on posetrack data.
@nikhilaravi Actually I removed the last layer of author-provided COCO model. I added random initialized layer and the output size = 15. I trained this on posetrack 17 training set.
Hello，what’ s your model peformance? And can you share your code about your operation mentioned above? Thanks!
Sure. Reply to me if you still want it and I will add some comments. It reached 69.6 mAP on Posetrack 2017 validation set.
Also I am interested in the code about tracking, can you share me about the tracking code. Much thanks :yum: My email can be reached at [email protected]
I am also interested in evaluating the model on posetrack data.
@nikhilaravi Actually I removed the last layer of author-provided COCO model. I added random initialized layer and the output size = 15. I trained this on posetrack 17 training set.
Hello，what’ s your model peformance? And can you share your code about your operation mentioned above? Thanks!
Sure. Reply to me if you still want it and I will add some comments. It reached 69.6 mAP on Posetrack 2017 validation set.
Also I am interested in the code about tracking, can you share me about the tracking code. Much thanks 😋 My email can be reached at [email protected]
You can browse my repo. Its name is nise_embedding and it is a mess...you may have to look into it a bit and feel free to propose issues.