Vision Language Python Packages

cn-clip

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

latent-gate

VL-JEPA inspired pipeline — compress images/text locally via Ollama, send compact payloads to any LLM API. Cut token costs by ~80%.

proto-clip-toolkit

Code release for Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning | IROS 2024

ddd-dataset

A detection/segmentation dataset with labels characterized by intricate and flexible expressions. "Described Object Detection: Liberating Object Detection with Flexible Expressions" (NeurIPS 2023).

vlm-eval-harness

CLI for multimodal (vision-language) model evaluation with JSON/CSV logs.

nw-groundingdino

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

gdinopy

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

groundingdino-iscas

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

groundingdino-yl

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

gddet

open-set object detector

groundingdino-mod

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

mmeval-vrag

Evaluation Framework for Multimodal RAG Systems