Negar Heidari

Are the failing tests related to my PR? As I see, it's object_detection and human_model_generation.

> Thank you for the fixes so far @negarhdr! > > Unfortunately, i still get an error from the ROS node: > > ``` > Error on trying to read...

> > I actually cannot run the ROS node on our servers, and that's why I didn't notice the bugs. > > It's ok i can test the ROS node...

> ``` > TypeError: Expected Ptr for argument 'src' > ``` I re-implemented demo and it is now much simplified and easier to track. You can try the image and...

Hi @pradeep-pyro , Thank you for the interesting work and releasing its code. I also have the same issue with reproducing the results for the self-supervised part on Solidletters dataset,...

Hi @pradeep-pyro, Thank you for your response. I trained the model on SolidLetters with your code and the Linear SVM Acc is around 57% on test set of SolidLetters which...

Yes, the AMI score for k-means is also very low (around 0.2), which is above 0.4 in the paper. Thanks for checking, looking forward to seeing the results .

Hi, Thanks for your comment. The models are trained on a dataset in which a maximum of 2 persons are in the scene performing an action. If there are more...

Hi, Thanks for your interest in my work. The code is integrated in OpenDR toolkit and a demo is available there: https://github.com/opendr-eu/opendr/blob/master/projects/perception/skeleton_based_action_recognition/demos/demo.py In order to train the models on a...