This package helps extract i3D features with ResNet-50 backbone given a folder of videos
Project description
Hello, I am Hao Vy Phan. I have develop this package using ResNet-50 to convert a video into an extracted i3D features numpy file.
Overview
Input: a directory which store 1 or more videos.
Output: 1 or many .npy files (extracted i3D features). Each features file is shaped n/16 * 2048 where n is the number of frames in the video
If there is a problem installing or implementing this package, please do not hesitate to contact me via my email. I am pleased to have people use my product.
Usage
Installation
Before installing my package, please install these pakages:
* Or find your own python OS version of torch from this link: https://download.pytorch.org/whl/cu113/torch_stable.html
Installing them through pip install may raise errors. You can download the wheel files from the above links and run this code:
pip install torchvision-0.11.2+cu113-cp38-cp38-win_amd64.whl
pip install torchaudio-0.10.1+cu113-cp38-cp38-win_amd64.whl
pip install torch-1.10.1+cu113-cp38-cp38-win_amd64.whl
pip install opencv_python-4.5.5-cp38-cp38-win_amd64.whl
After 4 above packages, to install i3dFeatureExtraction package into your Python environment, run this code on your terminal:
pip install i3dFeatureExtraction
Or install a specific version:
pip install i3dFeatureExtraction==x.x.x
Implementing
The main function of this package is FeatureExtraction which converts a directory of videos into numpy feature files.
from i3dFeatureExtraction import FeatureExtraction
FeatureExtraction.generate(
outputpath = "directory/to/store/output/numpy/files",
datasetpath="directory/of/input/videos",
pretrainedpath = "path/to/i3D/pretrained/weight",
sample_mode = "oversample/center_crop"
)
Structure
I am not good at drawing UML diagram but I hope this image helps illustrate the package’s structure.
Credits
This code is based on the following repositories:
* pytorch-i3d-feature-extraction
* E2E-Action-Segmentation/feature_extraction/
I would like to extend a special thank-you to the original authors of these repositories for providing the foundation on which this implementation is built.
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 i3dFeatureExtraction-0.2.8.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 388ebe0e029b1cdc15acf88c79182c73ebdb956bab467820a0273c3c93c0dec7 |
|
MD5 | 853321d6c05abced8250f739dd418a8b |
|
BLAKE2b-256 | 82e364c64cca8f03354559554dc407ceb03b1694d215cfbbef8853bc743e41a3 |
Hashes for i3dFeatureExtraction-0.2.8-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 97224842fdd0dc3ae9c6af6a7f6db1b0420690b523775ea07d21e37c7442a96b |
|
MD5 | 2b2cca8601aad2602f58ceddf7d6b775 |
|
BLAKE2b-256 | e157c1d2c638a3ffb7ad91d8b0bb5527c8a9a0dbe7e0106bcbe347cb352b8459 |