mmaction2
mmcv
Our great sponsors
| mmaction2 | mmcv | |
|---|---|---|
| 5 | 4 | |
| 3,884 | 5,596 | |
| 3.3% | 2.1% | |
| 7.8 | 7.8 | |
| 16 days ago | 1 day 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
mmcv
-
MMDeploy: Deploy All the Algorithms of OpenMMLab
MMCV: OpenMMLab foundational library for computer vision.
- Mmcv - Openmmlab computer vision foundation
-
An elegant and strong PyTorch Trainer
I opened source some works (AAAI 21 SeqNet, ICCV 21 MAED, etc) and earned more than 500 stars. After referring to some popular projects (detectron2, pytorch-image-models, and mmcv), based on my personal development experience, I developed a SIMPLE enough, GENERIC enough, and STRONG enough PyTorch Trainer: core-pytorch-utils, also named CPU. CPU covers most details in the process of training a deep neural network, including:
-
Why do practitioners still use regular tensorflow? [D]
Pretty much any custom layer, loss, ops, etc. For some of the most common ones used for objection detection, see here, examples include rotated iou/nms, deformable convolutions, focal loss variants, sync batch norm, etc.
What are some alternatives?
mmpose - OpenMMLab Pose Estimation Toolbox and Benchmark.
pytorch-image-models - PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNet-V3/V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
compare_gan - Compare GAN code.
TensorFlow2.0_Notebooks - Implementation of a series of Neural Network architectures in TensorFow 2.0
mmflow - OpenMMLab optical flow toolbox and benchmark
pytorch-lightning - Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.
temporal-shift-module - [ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding
detectron2 - Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
Video-Dataset-Loading-Pytorch - Generic PyTorch dataset implementation to load and augment VIDEOS for deep learning training loops.
mmrotate - OpenMMLab Rotated Object Detection Toolbox and Benchmark
aiqc - End-to-end deep learning on your desktop or server.