pytorch-lightning
mmdetection
Our great sponsors
pytorch-lightning | mmdetection | |
---|---|---|
8 | 23 | |
26,611 | 27,433 | |
3.0% | 1.9% | |
9.9 | 8.7 | |
about 23 hours ago | 9 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.
pytorch-lightning
-
Como empezar con inteligencia artificial?
https://see.stanford.edu/Course/CS229 https://lightning.ai/ https://www.youtube.com/watch?v=00s9ireCnCw&t=57s https://towardsdatascience.com/
-
Best practice for saving logits/activation values of model in PyTorch Lightning
I've been wondering on what is the recommended method of saving logits/activations using PyTorch Lightning. I've looked at Callbacks, Loggers and ModelHooks but none of the use-cases seem to be for this kind of activity (even if I were to create my own custom variants of each utility). The ModelCheckpoint Callback in its utility makes me feel like custom Callbacks would be the way to go but I'm not quite sure. This closed GitHub issue does address my issue to some extent.
-
We just release a complete open-source solution for accelerating Stable Diffusion pretraining and fine-tuning!
Our codebase for the diffusion models builds heavily on OpenAI's ADM codebase , lucidrains, Stable Diffusion, Lightning and Hugging Face. Thanks for open-sourcing!
-
An elegant and strong PyTorch Trainer
For lightweight use, pytorch-lightning is too heavy, and its source code will be very difficult for beginners to read, at least for me.
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 the 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
-
[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
-
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
-
I trained a neural net to watch Super Smash Bros
I used the PointRend implementation from the mmdet project https://github.com/open-mmlab/mmdetection
- bike classification advice sought for used bike aggregator
-
I want to create a pill counter using points instead of bounding boxes. What model should I train from?
If you are really that lazy: use bboxes of the fixed size placed in the center of the pill. The pill does not have to fit into the box - modern architectures see the image as a whole, not only the crop in the box. For example if you would train detection on labels which are shifted (add 30px to each label coordinate), the network would learn to place each box 30px next to the actual object. So just let small box represent the center of the pill. The problem will arise if you will use improperly configured architecture, i.e. if you will not change the anchors in SSD model. Try efficientdet architecture implemented in mmdetection or, the easiest, yolov5. These should work out of the box.
What are some alternatives?
detectron2 - Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
yolov5 - YOLOv5 🚀 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]
PaddleDetection - Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
mmdetection3d - OpenMMLab's next-generation platform for general 3D object detection.
sahi - Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
Mask_RCNN - Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
lnd - Lightning Network Daemon ⚡️
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
yolact - A simple, fully convolutional model for real-time instance segmentation.
yolact_edge - The first competitive instance segmentation approach that runs on small edge devices at real-time speeds.
Eclair - A scala implementation of the Lightning Network.