Keras implementation of skeleton transformer module
Project description
Skeleton Transformer in Keras
Keras implementation of "skeleton transformer module", which is mentioned in Skeleton-based Action Recognition with Convolutional Neural Networks.
Install
You can install this module from PyPI as skeraton
.
pip install skeraton
How to use
Module
skeraton.SkeletonTransformer
Parameters:
All parameters are required.
timesteps: Timesteps of input time-series data (equal to number of frames, mentioned as 'T' in the paper)
kpts_dim: Dimentions of keypoints (usually 2 (x, y) or 3 (x, y, z))
output_dim: Dimentions of output (mentioned as 'M' in the paper)
Input:
x: 3-dimentional tensor of shape (batchsize, timesteps, kpts_dim*N) where N is number of joints
Pytorch implementation
We also have Pytorch implementation of this module:
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file skeraton-0.1.0.tar.gz
.
File metadata
- Download URL: skeraton-0.1.0.tar.gz
- Upload date:
- Size: 3.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.8.8
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 843397f66ac174a11ddfbbcd81cae0af3fe136de7bb01b906f93acd86708accb |
|
MD5 | 7e86d263dcdde1790195399c788c786b |
|
BLAKE2b-256 | 74a56e5d5762f89f19646483d53650560f1926e82a34c5976c9e19f79f79cddd |
File details
Details for the file skeraton-0.1.0-py3-none-any.whl
.
File metadata
- Download URL: skeraton-0.1.0-py3-none-any.whl
- Upload date:
- Size: 3.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.8.8
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | ad4cbd395fc57f4cfae525f0669e21c65c5205085a962165680703266bd12667 |
|
MD5 | ca34dd18d7ffcd1b4b865c4665f8530d |
|
BLAKE2b-256 | 1bf9031a9b20b396fbd6191fd733a29de0495777e36e58acbc85372a854a8e7b |