M-PACT
Activity recognition model builder
A framework for building and testing activity recognition models using deep learning techniques.
A one stop shop for all of your activity recognition needs.
107 stars
8 watching
24 forks
Language: Python
last commit: almost 6 years ago
Linked from 1 awesome list
action-recognitionactivity-recognitionc3dcomputer-visionconvnetdeep-learningi3dinceptionlrcnlrcn-networkm-pactmpactresnetresnet-50temporal-segment-networkstensorflowtfrecordstsnvideo
jinwchoi/awesome-action-recognitionRelated projects:
| Repository | Description | Stars |
|---|---|---|
 minimaxir/automl-gs | Automates machine learning model creation and optimization for complex datasets | 1,857 |
 hx173149/c3d-tensorflow | An implementation of C3D-caffe on TensorFlow to recognize actions in videos. | 588 |
 jrbtaylor/activitynet | An implementation of the 2016 ActivityNet action recognition challenge using a CNN + LSTM approach with multi-threaded loading. | 54 |
 deepgram/kur | A system for quickly building and applying state-of-the-art deep learning models to new problems | 818 |
 hkust-knowcomp/r-net | An implementation of R-NET, a machine reading comprehension model using scaled multiplicative attention and variational dropout. | 578 |
 open-mmlab/mmaction | An open-source toolbox for action understanding from video data using PyTorch. | 1,863 |
 guillaume-chevalier/har-stacked-residual-bidir-lstms | An implementation of a deep neural network architecture for Human Activity Recognition using stacked residual bidirectional LSTM cells with TensorFlow. | 319 |
 andreas-bulling/actrectut | A toolkit providing a framework and tools for designing and evaluating activity recognition systems using inertial sensors. | 56 |
 microsoft/0xdeca10b | A framework for hosting and training machine learning models on a blockchain, enabling secure sharing and prediction without requiring users to pay for data or model updates. | 559 |
 zhiwu-huang/lienet | This project uses deep learning and Lie group theory to recognize actions from skeleton data | 64 |
 ma-shamshiri/human-activity-recognition | A human activity recognition project using accelerometer and gyroscope sensor data from phone and watch. | 101 |
 uw-madison-lee-lab/cobsat | Provides a benchmarking framework and dataset for evaluating the performance of large language models in text-to-image tasks | 30 |
 benedekrozemberczki/m-nmf | An implementation of Community Preserving Network Embedding using deep learning and matrix factorization techniques | 121 |
 coderskychen/action_recognition_zoo | A collection of codes and tools for building action recognition models using deep learning techniques | 244 |
 openbmb/viscpm | A family of large multimodal models supporting multimodal conversational capabilities and text-to-image generation in multiple languages | 1,098 |