A custom DeepStack model for detecting 16 human actions.

Overview

DeepStack_ActionNET

This repository provides a custom DeepStack model that has been trained and can be used for creating a new object detection API for detecting 16 human actions present in the ActionNET Dataset dataset. Also included in this repository is that dataset with the YOLO annotations.

>> Watch Video Demo

  • Download DeepStack Model and Dataset
  • Create API and Detect Objects
  • Discover more Custom Models
  • Train your own Model

Download DeepStack Model and Dataset

You can download the pre-trained DeepStack_ActionNET model and the annotated dataset via the links below.

Create API and Detect Actions

The Trained Model can detect the following actions in images and videos.

  • calling
  • clapping
  • cycling
  • dancing
  • drinking
  • eating
  • fighting
  • hugging
  • kissing
  • laughing
  • listening-to-music
  • running
  • sitting
  • sleeping
  • texting
  • using-laptop

To start detecting, follow the steps below

  • Install DeepStack: Install DeepStack AI Server with instructions on DeepStack's documentation via https://docs.deepstack.cc

  • Download Custom Model: Download the trained custom model actionnetv2.pt from this GitHub release. Create a folder on your machine and move the downloaded model to this folder.

    E.g A path on Windows Machine C\Users\MyUser\Documents\DeepStack-Models, which will make your model file path C\Users\MyUser\Documents\DeepStack-Models\actionnet.pt

  • Run DeepStack: To run DeepStack AI Server with the custom ActionNET model, run the command that applies to your machine as detailed on DeepStack's documentation linked here.

    E.g

    For a Windows version, you run the command below

    deepstack --MODELSTORE-DETECTION "C\Users\MyUser\Documents\DeepStack-Models" --PORT 80

    For a Linux machine

    sudo docker run -v /home/MyUser/Documents/DeepStack-Models -p 80:5000 deepquestai/deepstack

    Once DeepStack runs, you will see a log like the one below in your Terminal/Console

    That means DeepStack is running your custom actionnet.pt model and now ready to start detecting actions images via the API endpoint http://localhost:80/v1/vision/custom/actionnet or http://your_machine_ip:80/v1/vision/custom/actionnet

  • Detect actions in image: You can detect objects in an image by sending a POST request to the url mentioned above with the paramater image set to an image using any proggramming language or with a tool like POSTMAN. For the purpose of this repository, we have provided a sample Python code below.

    • A sample image can be found in images/test.jpg of this repository

    • Install Python and install the DeepStack Python SDK via the command below

      pip install deepstack_sdk
    • Run the Python file detect.py in this repository.

      python detect.py
    • After the code runs, you will find a new image in images/test_detected.jpg with the detection visualized, with the following results printed in the Terminal/Console.

      Name: dancing
      Confidence: 0.91482425
      x_min: 270
      x_max: 516
      y_min: 18
      y_max: 480
      -----------------------
      

    • You can try running action detection for other images.

Discover more Custom Models

For more custom DeepStack models that has been trained and ready to use, visit the Custom Models sample page on DeepStack's documentation https://docs.deepstack.cc/custom-models-samples/ .

Train your own Model

If you will like to train a custom model yourself, follow the instructions below.

  • Prepare and Annotate: Collect images on and annotate object(s) you plan to detect as detailed here
  • Train your Model: Train the model as detailed here
You might also like...
NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions (CVPR2021)
NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions (CVPR2021)

NExT-QA We reproduce some SOTA VideoQA methods to provide benchmark results for our NExT-QA dataset accepted to CVPR2021 (with 1 'Strong Accept' and 2

Episodic Transformer (E.T.) is a novel attention-based architecture for vision-and-language navigation. E.T. is based on a multimodal transformer that encodes language inputs and the full episode history of visual observations and actions.
🎓Automatically Update CV Papers Daily using Github Actions (Update at 12:00 UTC Every Day)

🎓Automatically Update CV Papers Daily using Github Actions (Update at 12:00 UTC Every Day)

An experiment on the performance of homemade Q-learning AIs in Agar.io depending on their state representation and available actions
An experiment on the performance of homemade Q-learning AIs in Agar.io depending on their state representation and available actions

Agar.io_Q-Learning_AI An experiment on the performance of homemade Q-learning AIs in Agar.io depending on their state representation and available act

Python Tensorflow 2 scripts for detecting objects of any class in an image without knowing their label.
Python Tensorflow 2 scripts for detecting objects of any class in an image without knowing their label.

Tensorflow-Mobile-Generic-Object-Localizer Python Tensorflow 2 scripts for detecting objects of any class in an image without knowing their label. Ori

Python TFLite scripts for detecting objects of any class in an image without knowing their label.
Python TFLite scripts for detecting objects of any class in an image without knowing their label.

Python TFLite scripts for detecting objects of any class in an image without knowing their label.

Training Confidence-Calibrated Classifier for Detecting Out-of-Distribution Samples / ICLR 2018

Training Confidence-Calibrated Classifier for Detecting Out-of-Distribution Samples This project is for the paper "Training Confidence-Calibrated Clas

CCAFNet: Crossflow and Cross-scale Adaptive Fusion Network for Detecting Salient Objects in RGB-D Images
CCAFNet: Crossflow and Cross-scale Adaptive Fusion Network for Detecting Salient Objects in RGB-D Images

Code and result about CCAFNet(IEEE TMM) 'CCAFNet: Crossflow and Cross-scale Adaptive Fusion Network for Detecting Salient Objects in RGB-D Images' IEE

Implementation for the IJCAI2021 work "Beyond the Spectrum: Detecting Deepfakes via Re-synthesis"

Beyond the Spectrum Implementation for the IJCAI2021 work "Beyond the Spectrum: Detecting Deepfakes via Re-synthesis" by Yang He, Ning Yu, Margret Keu

Comments
  • How to download a Custom Model action net v2.pt in Deepstack Server Docker?

    How to download a Custom Model action net v2.pt in Deepstack Server Docker?

    Tell me how to load a custom action network model correctly v2.pt in the Deepstack server docker? Did I do the right thing?

    DeepStack: Version 2021.09.01 I created the /model store/detection folders and threw the action net file there v2.pt image

    After the reboot, I got a v1/vision/custom/action net v2 entry in the logs. Did I do the right thing? It just confuses me that there is a v1/vision/custom/action net v2 entry in the logs, and the rest are written like this.

    /v1/vision/face
    /v1/vision/face/recognize
    ....
    

    image

    Is it necessary to enter here as in the case of face and object recognition? image image

    opened by DivanX10 0
Releases(v2)
  • v2(Aug 26, 2021)

    Version 2 of the DeepStack Custom Model for object detection API to detect human actions in images and videos. It detects the following actions

    • calling
    • clapping
    • cycling
    • dancing
    • drinking
    • eating
    • fighting
    • hugging
    • kissing
    • laughing
    • listening-to-music
    • running
    • sitting
    • sleeping
    • texting
    • using-laptop

    Download the model actionnetv2.pt from the Assets section (below) in this release.

    This Model is a YOLOv5x DeepStack custom model and that was trained for 150 epochs, generating a best model with the following evaluation result.

    [email protected]: 0.995 [email protected]: 0.913

    Source code(tar.gz)
    Source code(zip)
    actionnetv2.pt(169.41 MB)
  • v1(Aug 14, 2021)

    A DeepStack Custom Model for object detection API to detect human actions in images and videos. It detects the following actions

    • calling
    • clapping
    • cycling
    • dancing
    • drinking
    • eating
    • fighting
    • hugging
    • kissing
    • laughing
    • listening-to-music
    • running
    • sitting
    • sleeping
    • texting
    • using-laptop

    Download the model actionnet.pt from the Assets section (below) in this release.

    This Model is a YOLOv5x DeepStack custom model and that was trained for 150 epochs, generating a best model with the following evaluation result.

    [email protected]: 0.9858 [email protected]: 0.8051

    Source code(tar.gz)
    Source code(zip)
    actionnet.pt(169.41 MB)
Owner
MOSES OLAFENWA
Software Engineer @Microsoft , A self-Taught computer programmer, Deep Learning, Computer Vision Researcher and Developer. Creator of ImageAI.
MOSES OLAFENWA
A custom DeepStack model that has been trained detecting ONLY the USPS logo

This repository provides a custom DeepStack model that has been trained detecting ONLY the USPS logo. This was created after I discovered that the Deepstack OpenLogo custom model I was using did not contain USPS.

Stephen Stratoti 9 Dec 27, 2022
Python scripts for performing 3D human pose estimation using the Mobile Human Pose model in ONNX.

Python scripts for performing 3D human pose estimation using the Mobile Human Pose model in ONNX.

Ibai Gorordo 99 Dec 31, 2022
Example-custom-ml-block-keras - Custom Keras ML block example for Edge Impulse

Custom Keras ML block example for Edge Impulse This repository is an example on

Edge Impulse 8 Nov 2, 2022
Demonstrates how to divide a DL model into multiple IR model files (division) and introduce a simplest way to implement a custom layer works with OpenVINO IR models.

Demonstration of OpenVINO techniques - Model-division and a simplest-way to support custom layers Description: Model Optimizer in Intel(r) OpenVINO(tm

Yasunori Shimura 12 Nov 9, 2022
[CVPR2021] UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles

UAV-Human Official repository for CVPR2021: UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicle Paper arXiv Res

null 129 Jan 4, 2023
Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors, CVPR 2021

Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors Human POSEitioning System (H

Aymen Mir 66 Dec 21, 2022
Human Action Controller - A human action controller running on different platforms.

Human Action Controller (HAC) Goal A human action controller running on different platforms. Fun Easy-to-use Accurate Anywhere Fun Examples Mouse Cont

null 27 Jul 20, 2022
StyleGAN-Human: A Data-Centric Odyssey of Human Generation

StyleGAN-Human: A Data-Centric Odyssey of Human Generation Abstract: Unconditional human image generation is an important task in vision and graphics,

stylegan-human 762 Jan 8, 2023
Where2Act: From Pixels to Actions for Articulated 3D Objects

Where2Act: From Pixels to Actions for Articulated 3D Objects The Proposed Where2Act Task. Given as input an articulated 3D object, we learn to propose

Kaichun Mo 69 Nov 28, 2022
Allows including an action inside another action (by preprocessing the Yaml file). This is how composite actions should have worked.

actions-includes Allows including an action inside another action (by preprocessing the Yaml file). Instead of using uses or run in your action step,

Tim Ansell 70 Nov 4, 2022