mmaction2
mmdetection3d
Our great sponsors
mmaction2 | mmdetection3d | |
---|---|---|
5 | 3 | |
3,884 | 4,790 | |
3.3% | 4.6% | |
7.8 | 7.7 | |
17 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.
mmaction2
-
How good does contextual action recognition get?
Mmaction2: https://github.com/open-mmlab/mmaction2 Has some examples.
-
MMDeploy: Deploy All the Algorithms of OpenMMLab
MMAction2: OpenMMLab's next-generation action understanding toolbox and benchmark.
-
[D] Deep Learning Framework for C++.
I agree with you for most of the time this can work but there are some models that have certain layers that are not supported by ONNX. An example would be Spatiotemporal models in mmaction2 from open-mmlab.
-
Textbook or blogs for video understanding
No book or blog, but a great framework: https://github.com/open-mmlab/mmaction2
-
Applications of Deep Neural Networks [pdf]
shameless ad: try mmaction2, where every result is reproducible https://github.com/open-mmlab/mmaction2 . Modelzoo: https://mmaction2.readthedocs.io/en/latest/modelzoo.html
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?
mmpose - OpenMMLab Pose Estimation Toolbox and Benchmark.
mmdetection - OpenMMLab Detection Toolbox and Benchmark
compare_gan - Compare GAN code.
yolov5 - YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
mmflow - OpenMMLab optical flow toolbox and benchmark
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.
temporal-shift-module - [ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding
3d-multi-resolution-rcnn - Official PyTorch implementaiton of the paper "3D Instance Segmentation Framework for Cerebral Microbleeds using 3D Multi-Resolution R-CNN."
Video-Dataset-Loading-Pytorch - Generic PyTorch dataset implementation to load and augment VIDEOS for deep learning training loops.
yolov3 - YOLOv3 in PyTorch > ONNX > CoreML > TFLite
mmrotate - OpenMMLab Rotated Object Detection Toolbox and Benchmark
autogluon - AutoGluon: Fast and Accurate ML in 3 Lines of Code