yjxiong/tsn-pytorch
Temporal Segment Networks (TSN) in PyTorch
This project helps machine learning researchers and computer vision engineers train and evaluate models for video activity recognition. It takes raw video data or pre-extracted optical flow information as input. It outputs trained models that can classify actions within videos and performance scores for these models. This tool is for researchers focusing on video-based action understanding.
1,085 stars. No commits in the last 6 months.
Use this if you are a researcher or engineer who wants to reproduce or build upon the original Temporal Segment Networks (TSN) for video action recognition using PyTorch.
Not ideal if you are looking for a more comprehensive and actively maintained toolkit for various video understanding tasks, in which case the MMAction project is recommended.
Stars
1,085
Forks
308
Language
Python
License
BSD-2-Clause
Category
Last pushed
Jun 21, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yjxiong/tsn-pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
deepinv/deepinv
DeepInverse: a PyTorch library for solving imaging inverse problems using deep learning
mhamilton723/STEGO
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
fidler-lab/polyrnn-pp
Inference Code for Polygon-RNN++ (CVPR 2018)
pyxu-org/pyxu
Modular and scalable computational imaging in Python with GPU/out-of-core computing.
oeway/pytorch-deform-conv
PyTorch implementation of Deformable Convolution