RNN-for-Human-Activity-Recognition-using-2D-Pose-Input

RNN-for-Human-Activity-Recognition-using-2D-Pose-Input copied to clipboard

jren2019

I am trying to convert the json from tf-open-pose to txt format. Should I use run_openpose.sh for this purpose? if not should I make my own script? Please help!

RaghunandanVenkatesh

Accuracy for the prediction in real time

4

Hello Guys, I was wondering if it possible to find the accuracy for my prediction when running in real time? I see from your model(shown below),the prediction returns the element...

shreyah

Would the model work on videos where there are multiple actions and these are to be temporally detected?

1

Hi, Nice project. I was wondering would the model perform well on videos where an agent performs multiple actions throughout the video. Especially when these actions might have an inherent...

burhanusman

Can you provide the extracted skeleton features ?

5

Great project！ Can you provide the extracted skeleton features ? **DATASET_PATH = "data/HAR_pose_activities/database/"** thank you～

wxw420

Question: n_steps

1

Hi Stuart! Can I ask you how did you choose: n_steps = 32? Does it have to do with the average length of clips in the dataset? Were they all...

SlavaKeshkov

Where the train.py and visualization.py?

1

wulixunhua

Hey just wanted to tell you that openPOSE updated their json output format (https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/doc/output.md) because they added a new 3-D keypoint reconstruction module. So now, in Line 64: pose_keypoints =...

VicenteQueiroz

Hello there, I would like to ask you about the results in your experiments - 2D pose and raw RGB images, which one is better ? - Combine the 2D...

leviethung2103

Problem in inference part

1

Hello @stuarteiffert , thank you for your code!Really nice work! Could you help me solving the following problem? I want to do inference with a new X-train.txt that I've already...

OliviaNocentini