Library for viewing, augmenting, and handling .pose files
Project description
Pose Format
This repository aims to include a complete toolkit for working with poses. It includes a new file format with Python and Javascript readers and writers, in hope to make usage simple.
The File Format
The format supports any type of poses, arbitrary number of people, and arbitrary number of frames (for videos).
The main idea is having a header
with instructions on how many points exists, where, and how to connect them.
The binary spec can be found in lib/specs/v0.1.md.
Python Usage
pip install pose-format
To load a .pose
file, use the PoseReader
class:
from pose_format.pose import Pose
buffer = open("file.pose", "rb").read()
p = Pose.read(buffer)
By default, it uses NumPy for the data, but you can also use torch
and tensorflow
by writing:
from pose_format.pose import Pose
from pose_format.torch.pose_body import TorchPoseBody
from pose_format.tensorflow.pose_body import TensorflowPoseBody
buffer = open("file.pose", "rb").read()
p = Pose.read(buffer, TorchPoseBody)
p = Pose.read(buffer, TensorflowPoseBody)
Loading OpenPose data
To load an OpenPose directory
, use the load_openpose_directory
utility:
from pose_format.utils.openpose import load_openpose_directory
directory = "/path/to/openpose/directory"
p = load_openpose_directory(directory, fps=24, width=1000, height=1000)
Data Normalization
To normalize all of the data to be in the same scale, we can normalize every pose by a constant feature of their body. For example, for people we can use the average span of their shoulders throughout the video to be a constant width.
p.normalize(p.header.normalization_info(
p1=("pose_keypoints_2d", "RShoulder"),
p2=("pose_keypoints_2d", "LShoulder")
))
Data Augmentation
p.augment2d(rotation_std=0.2, shear_std=0.2, scale_std=0.2)
Data Interpolation
To change the frame rate of a video, using data interpolation, use the interpolate_fps
method which gets a new fps
and a interpolation kind
.
p.interpolate_fps(24, kind='cubic')
p.interpolate_fps(24, kind='linear')
Testing
Use bazel to run tests
cd pose_format
bazel test ... --test_output=errors
Alternatively, use a different testing framework to run tests, such as regular Python unit testing. To run an individual test file:
python -m unittest discover -s pose_format/utils -p 'openpose_test.py'
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
Hashes for pose_format-0.0.6-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5c21205d88a1c0fcd9773f66b91247c83f52fd4557b5861896d85182a269f83c |
|
MD5 | c863136073b8aaa3a0effedd0da1e09e |
|
BLAKE2b-256 | 86cd163a4434dadaefc546ffcc07237a7fb9d57dd5e8bc7cdd048c7c07b681f2 |