guerrifrancesco

Tracking and JSON mistakes

9

Hi, I'm trying to start from a certain video and obtain a JSON with the 2D poses in order to use it with another code to transform 2D skeletons to...

Hi. I'm using Tensorflow 2.0.0 version and I had some problems with convert.py At every line with `np.ndarray(shape=(1,), dtype='int32') #buffer=weights_file.read(4)` I obtained the following error: `TypeError: buffer is too small...

Hi. I analyzed the code and I've seen that in test mode the output for each input is an array with shape[32, 5, 60] and then transformed to [32,60] after...

Hi, thanks for your work! I'm watching the code and I wonder if it is possible to do inference on a generic video. I mean, if I use NTU pre-trained...

Human3.6M evaluation with non-GT 2D keypoints

1

Hi, I would evaluate GAST-Net using 2D keypoints from a 2d pose estimation framework. In the code you provided, 2D keypoints for evaluation are taken by the projection of the...

Hi. I'd like to run this framework on my own 3D keypoints annotation with H36M or NTU format to predict actions. Is it possible? How can I do it?