detectron2
cleanlab
Our great sponsors
detectron2 | cleanlab | |
---|---|---|
48 | 69 | |
28,380 | 8,153 | |
1.6% | 5.0% | |
7.5 | 9.4 | |
7 days ago | about 18 hours ago | |
Python | Python | |
Apache License 2.0 | GNU Affero General Public License v3.0 |
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.
detectron2
-
Instance segmentation of small objects in grainy drone imagery
And not enough true positives either. Add more augmentations in the config. Also make sure the config is set correctly, so that Detectron2 isn't skipping background images: https://github.com/facebookresearch/detectron2/issues/80
Similarly, I am using the more simple R50-FPN backbone (https://github.com/facebookresearch/detectron2/blob/main/MODEL_ZOO.md) which may be too simple for grainy, small object, segmentation tasks
Thank you, I will have a look at it. I'm not that knowledgeable about existing models. Detectron2 also provides different different backbones (https://github.com/facebookresearch/detectron2/blob/main/MODEL_ZOO.md). Is there a reason you recommend the segmentation-models library (apologies for the naive question)?
-
AI Real Time (lgd for cn)
Which is built on https://github.com/facebookresearch/detectron2
-
List of AI-Models
Click to Learn more...
-
good computer vision or deep learning projects in github
Detectron2 (GitHub: https://github.com/facebookresearch/detectron2) is a Facebook AI Research library with state-of-the-art object detection and segmentation algorithms in PyTorch.
-
Object Detection using PyTorch: Would you recommend a Framework (Detectron2, MMDetection, ...) or a project from scratch ?
That would be awesome. But I think that Detectron only provides RCNN, but I could be wrong. At least the model zoo on github looks like it.
-
PyTorch 2.0 Release
I could fine-tune a Detectron2 model a few months ago using PyTorch and MPS backend [1]. I'd be interested if it's working yet.
-
[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.
cleanlab
-
Automated Data Quality at Scale
Sharing some context here: in grad school, I spent months writing custom data analysis code and training ML models to find errors in large-scale datasets like ImageNet, work that eventually resulted in this paper (https://arxiv.org/abs/2103.14749) and demo (https://labelerrors.com/).
Since then, I’ve been interested in building tools to automate this sort of analysis. We’ve finally gotten to the point where a web app can do automatically in a couple of hours what I spent months doing in Jupyter notebooks back in 2019—2020. It was really neat to see the software we built automatically produce the same figures and tables that are in our papers.
The blog post shared here is results-focused, talking about some of the data and dataset-level issues that a tool using data-centric AI algorithms can automatically find in ImageNet, which we used as a case study. Happy to answer any questions about the post or data-centric AI in general here!
P.S. all of our core algorithms are open-source, in case any of you are interested in checking out the code: https://github.com/cleanlab/cleanlab
-
[N] Fine-Tuning OpenAI Language Models with Noisily Labeled Data (37% error reduction)
If you have trained a speech-to-text model and are able to get its probabilistic predictions over the word/token at each position, then you can use the token_classification module in our open-source cleanlab library for this purpose.
-
[P] We are building a curated list of open source tooling for data-centric AI workflows, looking for contributions.
Currently, you have to do a bit of hacking: https://github.com/cleanlab/cleanlab/issues/586
How about cleanlab? It works for any data you can train a classifier or get embeddings on (text, tabular, image, audio, etc). We just released some new features as well. Currently, cleanlab can automatically:
-
[Research] ActiveLab: Active Learning with Data Re-Labeling
I recently published a paper introducing this novel method and an open-source Python implementation that is easy-to-use for all data types (image, text, tabular, audio, etc). For data scientists, I’ve made a quick Jupyter tutorial to run ActiveLab on your own data. For ML researchers, I’ve made all of our benchmarking code available for reproducibility so you can see for yourself how effective ActiveLab is in practice.
- Introduction to Data-Centric AI
-
Cleanlab: the standard framework for Data-centric AI hits 5,000 GitHub stars!
It’s not a coincidence that thousands of data scientists are already using [cleanlab](https://github.com/cleanlab/cleanlab). Our team has spent many long days and nights working to expand our suite of data-centric AI tools you need to improve the quality of your ML data. We strive to produce cutting-edge research and contribute open-source code — all for free.
link to cleanlab package: https://github.com/cleanlab/cleanlab
-
cleanlab: an open-source python framework for data-centric AI
I've been busy building a standard open-source library for data-centric AI: https://github.com/cleanlab/cleanlab/
- [Discussion] - "data sourcing will be more important than model building in the era of foundational model fine-tuning"
What are some alternatives?
mmdetection - OpenMMLab Detection Toolbox and Benchmark
yolov5 - YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
openpose - OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
U-2-Net - The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."
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]
rembg - Rembg is a tool to remove images background
deep-text-recognition-benchmark - Text recognition (optical character recognition) with deep learning methods, ICCV 2019
car-damage-detection - Detectron2 for car damage detection using custom dataset
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
ai-background-remove - Cut out objects and remove backgrounds from pictures with artificial intelligence
alibi-detect - Algorithms for outlier, adversarial and drift detection
lightning-bolts - Toolbox of models, callbacks, and datasets for AI/ML researchers.