HASS-Deepstack-object
mmdetection
HASS-Deepstack-object | mmdetection | |
---|---|---|
2 | 23 | |
403 | 27,833 | |
- | 1.4% | |
5.3 | 8.4 | |
about 1 year ago | 8 days ago | |
Python | Python | |
MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
HASS-Deepstack-object
-
Deepstack: Open-Source AI Server
Hi everyone, I am Moses Olafenwa, the CEO and Head of Operations of the company DeepQuest AI (now a UK company based in Greenwich, London). First, apologies for the missing information of our names on the about page. The deepquestai.com website hasn't been updated recently due to our team being a small one and having lots to do.
About DeepStack: DeepStack is an artificial intelligence server we developed late 2018 to empower developers to easily setup, integrate and leverage AI functionalities (blog post: https://medium.com/deepquestai/deepstack-build-ai-powered-ap... ) fully on the edge or their private cloud machines.
Today, DeepStack is available as a Docker image on Docker Hub and native application for Windows, with support for CPUs, modern NVIDIA GPUs, Jetson devices, ARM devices, Linux and MacOS with over 10 millions installs on Docker Hub ( https://hub.docker.com/r/deepquestai/deepstack ). It include functionalities such as Face Recognition/Detection APIs, common objects detection, image superresolution, custom detection models to detect any custom object of interest and many more. You can learn more about the product and using it via the documentation linked below
https://docs.deepstack.cc
DeepStack has a very active community on the official forum https://forum.deepstack.cc and other forums like HomeAssistant ( https://community.home-assistant.io/t/face-and-person-detect... ), IPCamTalk( https://ipcamtalk.com/tags/deepstack/ ) and YouTube ( https://www.youtube.com/results?search_query=deepstack+ai+se... )
From year 2019 after we released DeepStack till early, 2021 the project was largely developed and maintained by John Olafenwa (the creator of the AI server) and I; pretty hard for 2 folks with day job to keep up with everything involved in the project which is why some of our sites are not fully updated. That is about to change in 2022 as we grew to a team of 6 late last year and growing to ensure we keep developing, maintaining and improving DeepStack for the almost a million developers leveraging the server to integrate AI.
-
For what do you use your Jetson Nano?
Running Deepstack on it, paired with HASS-Deepstack-object in Home Assistant.
mmdetection
-
Semantic segementation
When I look for benchmarks I always start here https://paperswithcode.com/task/instance-segmentation/codeless it has the lists of datasets to measure models accross lots o papers. Many are very specific models with low support or community but it gives you a good idea of ββthe state of the art. It also lists repositories related to good community. https://github.com/open-mmlab/mmdetection seems very active and the one that is being used the most, you could use the models that it has integrated in its model zoo, within the same repository. It has the benchmarks to compare those same models and some of them are from 2022
-
How to Convert Model Mask into Polygon and save JSON?
MODEL: https://github.com/open-mmlab/mmdetection
-
Object Detection Model for Custom Dataset Training?
Would it make sense to work with OpenMMLab (https://github.com/open-mmlab/mmdetection) or Pytorch-image-models (https://github.com/rwightman/pytorch-image-models#models) since they offer a variety of models?
-
[P] Image search with localization and open-vocabulary reranking.
I wanted to have a few choices getting localization into image search (index and search time). I immediately thought of using a region proposal network (rpn) from mask-rcnn to create patches that can also be indexed and searched (and add the localisation). I figured it might be somewhat agnostic to classes. I did not want to use mmdetection or detectron2 due to their dependencies and just getting the rpn was not worth it. I was encouraged by the PyTorch native implementations of detection/segmentation models but ended up finding yolox the best.
-
MMDeploy: Deploy All the Algorithms of OpenMMLab
MMDetection: OpenMMLab detection toolbox and benchmark.
-
Removing the bounding box generated by OnnxRuntime segmentation
I have a semantic segmentation model trained using the mmdetection repo. Then it is converted to the ONNX format using the mmdeploy repo.
-
Keras vs Tensorflow vs Pytorch for a Final year Project
E.g. If you consider it an object detection problem it is: detect and localise all the pedestrians in a frame, and classify them by their (intended) action. IMO the easiest way to do this would be with mmdetection, which is built on top of pytorch. Just label your dataset, build a config, and boom you have a model. Inference with that model in only a few lines of code, you won't really need to learn too much to get started.
-
DeepSort with PyTorch(support yolo series)
MMDetection
-
[D] Pre-trained networks and batch normalization
For example, in mmdetection, they expose options in their config & implementation to freeze batch norm layers in backbones and in this config, norm_eval is set to True meaning to freeze tracking of batch norm stats, while the ResNet backbone is frozen up to the 1st stage. Example of their backbone implementation can be found here.
-
Config files in plain Python
MMDetection uses config Python scripting. It's easier to define nn.Module objects other than writing class name in a json config file
What are some alternatives?
frigate - NVR with realtime local object detection for IP cameras
detectron2 - Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
yolov3 - YOLOv3 in PyTorch > ONNX > CoreML > TFLite
yolov5 - YOLOv5 π in PyTorch > ONNX > CoreML > TFLite
pytorch-lightning - Build high-performance AI models with PyTorch Lightning (organized PyTorch). Deploy models with Lightning Apps (organized Python to build end-to-end ML systems). [Moved to: https://github.com/Lightning-AI/lightning]
ImageAI - A python library built to empower developers to build applications and systems with self-contained Computer Vision capabilities
PaddleDetection - Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
DeepStack - The World's Leading Cross Platform AI Engine for Edge Devices
mmdetection3d - OpenMMLab's next-generation platform for general 3D object detection.
Mask_RCNN - Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
sahi - Framework agnostic sliced/tiled inference + interactive ui + error analysis plots