twitter-research / image-crop-analysisLinks
Code for reproducing our analysis in the paper titled: Image Cropping on Twitter: Fairness Metrics, their Limitations, and the Importance of Representation, Design, and Agency
β253Updated 3 years ago
Alternatives and similar repositories for image-crop-analysis
Users that are interested in image-crop-analysis are comparing it to the libraries listed below
Sorting:
- Application for searching images from natural language queriesβ46Updated 3 years ago
- Break neural networks in your browser π¦ΉββοΈβ151Updated 3 years ago
- β145Updated 3 years ago
- β42Updated 11 months ago
- Dataset for the Collection of Facial Expressions from Japanese Artworkβ168Updated 3 years ago
- TensorFlow Similarity is a python package focused on making similarity learning quick and easy.β1,022Updated last year
- An implementation of Additive Attentionβ149Updated 3 years ago
- MLOps for Vision Models (TensorFlow) from π€ Transformers with TensorFlow Extended (TFX)β115Updated 2 years ago
- Generate realistic Instagram captions using transformers π€β101Updated last year
- β54Updated 3 years ago
- Using AWS Lambda with Docker to deploy a deep learning modelβ23Updated 4 years ago
- Project demonstrating dual model deployment scenarios using Vertex AI (GCP).β34Updated 3 years ago
- β132Updated 3 years ago
- TF2 implementation of knowledge distillation using the "function matching" hypothesis from https://arxiv.org/abs/2106.05237.β87Updated 3 years ago
- This is a English-Japanese lexicon for Machine Learning and Deep Learning terminology.β37Updated 4 years ago
- https://blog.tensorflow.org/2021/12/continuous-adaptation-for-machine.htmlβ29Updated 3 years ago
- Python script to preprocess images of all PokΓ©mon to finetune ruDALL-Eβ137Updated 3 years ago
- A containerized REST API around OpenAI's CLIP model.β67Updated last year
- chaii: hindi and tamil question answeringβ35Updated 3 years ago
- Github action to upload datasets to kaggleβ24Updated 4 months ago
- Visual Similarity research at Fynd. Contains code to reproduce 2 of our research papers.