assembled-cnn
cvat
assembled-cnn | cvat | |
---|---|---|
1 | 26 | |
330 | 11,287 | |
0.6% | - | |
0.0 | 9.8 | |
over 3 years ago | 28 days ago | |
Python | TypeScript | |
Apache License 2.0 | MIT License |
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.
assembled-cnn
-
[R] ResNet strikes back: An improved training procedure in timm. There has been significant progress on best practices for training neural nets since ResNet's introduction in 2015. With such advances, a vanilla ResNet-50 reaches 80.4% top-1 accuracy on ImageNet without extra data or distillation.
As far as i know, the assemble-ResNet-50 (https://github.com/clovaai/assembled-cnn) gets 82.8% top-1, though they make some (minor) changes to ResNet-50 architecture.
cvat
-
Exploring Open-Source Alternatives to Landing AI for Robust MLOps
Another powerful resource is CVAT, the Computer Vision Annotation Tool which supports both image and video annotations with advanced capabilities such as interpolation of shapes between frames, making it highly suitable for computer vision.
-
Need help identifying a good open source data annotation tool
CVAT has an open source repo under MIT license: https://github.com/opencv/cvat I've not worked with it directly but it might be a good place to start.
-
OKENYO - Eyes to the Sky
ref https://github.com/opencv/cvat/issues/6061
-
Way to label yolov7 images fast
an open source annotation tool that integrates object detectors is CVAT https://github.com/opencv/cvat however, using your own detector might require some coding. there is an integration for yolov5, but without modification it only loads the pretrained models.
- [D] Choosing the image labeling tool
-
Segment Anything Model is now available in the open-source CVAT
This integration is currently available in the open-source version of Computer Vision Annotation Tool (http://github.com/opencv/cvat) and coming soon to CVAT.ai cloud (http://cvat.ai/)! Please use it for your computer vision projects to segment images faster.
-
How to build computer vision dataset labeling team in-house
You can download the CVAT docker from a github (Link) and install it yourself, keeping all data local. And here are two options - locally on your personal computer (or company server) or in your own cloud (there are instructions on how to do this with AWS).
-
CVAT Release v2.3.0: Brush tool, WebHooks, and Social auth
In this release, CVAT introduced new features based on our vision and suggestions in the CVAT community, plus addressed more than 20+ reported bugs.
-
CVAT Course. Lecture #3 - Integration
You can find more information here Waiting for your feedback here: Discord, LinkedIn, Gitter, GitHub
What are some alternatives?
biprop - Identify a binary weight or binary weight and activation subnetwork within a randomly initialized network by only pruning and binarizing the network.
label-studio - Label Studio is a multi-type data labeling and annotation tool with standardized output format
Naruto_Handsign_Classification - Naruto Hand Gesture Recognition with OpenCV and Transfer Learning
labelImg - LabelImg is now part of the Label Studio community. The popular image annotation tool created by Tzutalin is no longer actively being developed, but you can check out Label Studio, the open source data labeling tool for images, text, hypertext, audio, video and time-series data.
autogluon - AutoGluon: AutoML for Image, Text, Time Series, and Tabular Data [Moved to: https://github.com/autogluon/autogluon]
VoTT - Visual Object Tagging Tool: An electron app for building end to end Object Detection Models from Images and Videos.
autogluon - Fast and Accurate ML in 3 Lines of Code
coco-annotator - :pencil2: Web-based image segmentation tool for object detection, localization, and keypoints
One-Piece-Image-Classifier - A quick image classifier trained with manually selected One Piece images.
django-rest-framework - Web APIs for Django. 🎸
labelbox-custom-labeling-apps - Explore example custom labeling apps built with Labelbox SDK
make-sense - Free to use online tool for labelling photos. https://makesense.ai