encord-team / text-to-image-evalLinks
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.
☆54Updated 9 months ago
Alternatives and similar repositories for text-to-image-eval
Users that are interested in text-to-image-eval are comparing it to the libraries listed below
Sorting:
- ☆78Updated last month
- A minimal implementation of LLaVA-style VLM with interleaved image & text & video processing ability.☆96Updated 10 months ago
- Estimate dataset difficulty and detect label mistakes using reconstruction error ratios!☆26Updated 9 months ago
- Notebooks for fine tuning pali gemma☆117Updated 6 months ago
- Fine-tuning OpenAI CLIP Model for Image Search on medical images☆76Updated 3 years ago
- auto_labeler - An all-in-one library to automatically label vision data☆17Updated 9 months ago
- The official repo for the paper "VeCLIP: Improving CLIP Training via Visual-enriched Captions"☆246Updated 9 months ago
- From scratch implementation of a vision language model in pure PyTorch☆246Updated last year
- Easily get basic insights about your ML dataset☆40Updated last year
- A tool for converting computer vision label formats.☆76Updated last month
- Timm model explorer☆42Updated last year
- Run zero-shot prediction models on your data☆35Updated 10 months ago
- Supercharge Your PyTorch Image Models: Bag of Tricks to 8x Faster Inference with ONNX Runtime & Optimizations☆23Updated last year
- ☆59Updated last year
- Chat with Phi 3.5/3 Vision LLMs. Phi-3.5-vision is a lightweight, state-of-the-art open multimodal model built upon datasets which includ…☆34Updated 10 months ago
- AI assistant that can query visual datasets, search the FiftyOne docs, and answer general computer vision questions☆249Updated 10 months ago
- Self-Supervised Learning in PyTorch☆141Updated last year
- Simplify Your Visual Data Ops. Find and visualize issues with your computer vision datasets such as duplicates, anomalies, data leakage, …☆69Updated 5 months ago
- The most impactful papers related to contrastive pretraining for multimodal models!☆73Updated last year
- A FiftyOne Plugin that allows you to search across any modality in your videos!☆22Updated 5 months ago
- Which model is the best at object detection? Which is best for small or large objects? We compare the results in a handy leaderboard.☆90Updated last week
- Quick exploration into fine tuning florence 2☆334Updated last year
- Projects based on SigLIP (Zhai et. al, 2023) and Hugging Face transformers integration 🤗☆280Updated 8 months ago
- An ONNX-based implementation of the CLIP model that doesn't depend on torch or torchvision.☆74Updated last year
- 🤩 An AWESOME Curated List of Papers, Workshops, Datasets, and Challenges from CVPR 2024☆143Updated last year
- Code from the paper "Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models"☆92Updated 2 weeks ago
- Fine tuning OpenAI's CLIP model on Indian Fashion Dataset☆52Updated 2 years ago
- FiftyOne Plugin for finding common image quality issues☆33Updated last year
- ☆209Updated 2 years ago
- ☆43Updated last year