aesthetic-predictor
Image Aesthetic Predictor
Predicts aesthetic quality of images using CLIP model embeddings
A linear estimator on top of clip to predict the aesthetic quality of pictures
491 stars
13 watching
20 forks
Language: Jupyter Notebook
last commit: over 2 years ago Related projects:
Repository | Description | Stars |
---|---|---|
| Evaluates and compares the performance of various CLIP-like models on different tasks and datasets. | 632 |
| Predicts and improves visual realism in composite images using deep learning techniques | 64 |
| Web application that predicts facial beauty ratings from uploaded selfies using machine learning on a specific dataset. | 10 |
| A repository containing a collection of large datasets used for training and testing AI models, specifically designed to improve image-text matching capabilities. | 239 |
| A deep learning-based framework for image aesthetics assessment using a convolutional neural network structure | 112 |
| This project proposes a solution to predict salient areas in images using convolutional neural networks. | 186 |
| Provides pre-trained face detection and analysis models using large-scale image-text data | 281 |
| A library for learning audio embeddings from text and audio data using contrastive language-audio pretraining | 1,457 |
| A deep neural network architecture that predicts visual features from text to improve image and video caption retrieval | 69 |
| An implementation of a deep learning model for predicting chemical properties from molecular structure data | 30 |
| Converts images to various art styles using pre-trained machine learning models. | 227 |
| A deep learning framework for predicting material properties from composition information. | 94 |
| Trains neural networks to assess image aesthetics using pre-trained models and custom datasets | 539 |
| This project trains machine learning models to predict stock returns using various algorithms and techniques. | 1,745 |
| A neural network designed to learn and predict image features from binary encoded input | 1,370 |