sharpened-cosine-similarity
albumentations


sharpened-cosine-similarity | albumentations | |
---|---|---|
2 | 37 | |
254 | 14,562 | |
0.0% | 0.9% | |
0.0 | 9.7 | |
11 months ago | 7 days ago | |
Python | Python | |
MIT License | 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.
sharpened-cosine-similarity
-
Alternatives to Cosine Similarity
Don't forget Sharpened Cosine Similarity[0] which arose from this really interesting twitter thread [1].
[0] https://github.com/brohrer/sharpened-cosine-similarity
[1] https://twitter.com/_brohrer_/status/1232063619657093120
- Sharpened Cosine Distance as an Alternative for Convolutions
albumentations
- Albumentations: Fastest and most flexible image augmentation library
- Albumentations: Fast Image Augmentations
- Albumentations: Python library for fast image augmentations
- Albumentations: Fast and Flexible Image Augmentations
- Albumentations: Fast and flexible image augmentation library
-
Essential Deep Learning Checklist: Best Practices Unveiled
How to Accomplish: Use a combination of geometric transformations (e.g., rotation, scaling, cropping, flipping), color space adjustments (e.g., brightness, contrast, saturation), and other techniques (e.g., noise injection, blurring, cutout). Libraries such as ImgAug, DeepMind Augmentation, Albumentations, and NVIDIA DALI offer a wide range of ready-to-use augmentation techniques that can introduce the necessary diversity into your dataset.
-
Recapping the AI, Machine Learning and Data Science Meetup - May 30, 2024
In this presentation, we explore key strategies for boosting the adoption of open-source libraries, using Albumentations.ai as a case study. We will cover the importance of community engagement, continuous innovation, and comprehensive documentation in driving a project’s success. Through the lens of Albumentations.ai’s growth, attendees will gain insights into effective practices for promoting their open source projects within the machine learning and broader developer communities.
-
Recapping the AI, Machine Learning and Data Science Meetup — May 8, 2024
In this brief walkthrough, I will illustrate how to leverage open-source FiftyOne and Anomalib to build deployment-ready anomaly detection models. First, we will load and visualize the MVTec AD dataset in the FiftyOne App. Next, we will use Albumentations to test out augmentation techniques. We will then train an anomaly detection model with Anomalib and evaluate the model with FiftyOne.
-
Augment specific classes?
You can use albumentations if you are comfortable with using open source libraries https://github.com/albumentations-team/albumentations
What are some alternatives?
DeepMalwareDetector - A Deep Learning framework that analyses Windows PE files to detect malicious Softwares.
imgaug - Image augmentation for machine learning experiments.
convolution-vision-transformers - PyTorch Implementation of CvT: Introducing Convolutions to Vision Transformers
YOLO-Mosaic - Perform mosaic image augmentation on data for training a YOLO model
hub - A library for transfer learning by reusing parts of TensorFlow models.
labelme2coco - A lightweight package for converting your labelme annotations into COCO object detection format.
Convolution-From-Scratch - Implementation of the generalized 2D convolution with dilation from scratch in Python and NumPy
BlenderProc - A procedural Blender pipeline for photorealistic training image generation
SCS-CCT - CCT but using Sharpened Cosine Similarity
Mask-RCNN-TF2 - Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow 2.0
autoalbument - AutoML for image augmentation. AutoAlbument uses the Faster AutoAugment algorithm to find optimal augmentation policies. Documentation - https://albumentations.ai/docs/autoalbument/
VoTT - Visual Object Tagging Tool: An electron app for building end to end Object Detection Models from Images and Videos.

