mmdetection
mmdetection3d
Our great sponsors
mmdetection | mmdetection3d | |
---|---|---|
23 | 3 | |
27,742 | 4,790 | |
2.3% | 4.6% | |
8.7 | 7.7 | |
7 days ago | 5 days ago | |
Python | Python | |
Apache License 2.0 | 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.
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
mmdetection3d
-
What's the best model to get monocular 3d angle info
There are bunch of methods in this codebase, check it out. https://github.com/open-mmlab/mmdetection3d
-
MMDeploy: Deploy All the Algorithms of OpenMMLab
MMDetection3D: OpenMMLab's next-generation platform for general 3D object detection.
-
Master thesis on autonomous vehicles (cybersecurity aspect)
You create and test the attacks on datasets like Kitti, NuScenes, and many others. Basically you try to manipulate the input to a certain detection pipeline for example (You can find a lot of LiDAR and camera based detection pipelines here: https://github.com/open-mmlab/mmdetection3d and here https://github.com/open-mmlab/mmdetection). You try to manipulate the input so that it deceives the car to do what you need without having control to the car itself.
What are some alternatives?
detectron2 - Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
yolov5 - YOLOv5 π in PyTorch > ONNX > CoreML > TFLite
medicaldetectiontoolkit - The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.
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]
3d-multi-resolution-rcnn - Official PyTorch implementaiton of the paper "3D Instance Segmentation Framework for Cerebral Microbleeds using 3D Multi-Resolution R-CNN."
PaddleDetection - Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
yolov3 - YOLOv3 in PyTorch > ONNX > CoreML > TFLite
sahi - Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
autogluon - AutoGluon: Fast and Accurate ML in 3 Lines of Code
Mask_RCNN - Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
SimpleView - Official Code for ICML 2021 paper "Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline"