encord-team / text-to-image-eval
Evaluate custom and HuggingFace text-to-image/zero-shot-image-classification models like CLIP, SigLIP, DFN5B, and EVA-CLIP. Metrics include Zero-shot accuracy, Linear Probe, Image retrieval, and KNN accuracy.
☆34Updated last month
Related projects: ⓘ
- The official repo for the paper "VeCLIP: Improving CLIP Training via Visual-enriched Captions"☆214Updated 3 weeks ago
- ☆56Updated 6 months ago
- Run zero-shot prediction models on your data☆29Updated 2 months ago
- Fine-tuning OpenAI CLIP Model for Image Search on medical images☆73Updated 2 years ago
- ☆189Updated 10 months ago
- Self-Supervised Learning in PyTorch☆126Updated 6 months ago
- PyTorch code for hierarchical k-means -- a data curation method for self-supervised learning☆119Updated 3 months ago
- A tool for converting computer vision label formats.☆50Updated 9 months ago
- From scratch implementation of a vision language model in pure PyTorch☆149Updated 4 months ago
- Notebooks for fine tuning pali gemma☆33Updated last month
- ☆124Updated 10 months ago
- ☆20Updated this week
- Simplify Your Visual Data Ops. Find and visualize issues with your computer vision datasets such as duplicates, anomalies, data leakage, …☆65Updated 11 months ago
- Use Florence 2 to auto-label data for use in training fine-tuned object detection models.☆54Updated last month
- Easily get basic insights about your ML dataset☆30Updated 10 months ago
- ☆43Updated 5 months ago
- Timm model explorer☆36Updated 5 months ago
- ☆55Updated 3 months ago
- A framework for merging models solving different tasks with different initializations into one multi-task model without any additional tr…☆273Updated 8 months ago
- Computer Vision dataset analysis☆291Updated last month
- understanding model mistakes with human annotations☆104Updated last year
- The most impactful papers related to contrastive pretraining for multimodal models!☆38Updated 6 months ago
- [NeurIPS 2022] Official PyTorch implementation of Optimizing Relevance Maps of Vision Transformers Improves Robustness. This code allows …☆124Updated last year
- Continuation of an abandoned project fast-coco-eval☆55Updated last week
- My journey during 10 weeks of building FiftyOne plugins☆18Updated 10 months ago
- Awesome Fine-Grained Image Classification☆65Updated last month
- Repository for the paper: "TiC-CLIP: Continual Training of CLIP Models".☆90Updated 3 months ago
- Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.☆150Updated 5 months ago
- Streamlit component for image annotation.☆77Updated last month
- A light-weight implementation of ICCV2023 paper "Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Rei…☆77Updated 11 months ago