Examples and tutorials on using SOTA computer vision models and techniques. Learn everything from old-school ResNet, through YOLO and object-detection transformers like DETR, to the latest models like Grounding DINO and SAM.

An open source implementation of CLIP.

Video Foundation Models & Data for Multimodal Understanding

FastViT base model for use with Autodistill.

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.

GPT-4o (with Vision) module for use with Autodistill.

Scripts, algorithms and files for a rule-based and ML-based approach for binary classification of regulatory / non-regulatory sentences in EU legislative documents, as well as code for evaluating the accuracy of these approaches

Multi-Aspect Vision Language Pretraining - CVPR2024

Unofficial (Golang) Go bindings for the Hugging Face Inference API

[CVPR 2024] The official implementation of paper "Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training"

🥂 Gracefully face hCaptcha challenge with MoE(ONNX) embedded solution.

Comparing zero-shot and fine-tuned text classification transformer models across different review datasets

some useful colab files

Transformers, including the T5 and MarianMT, enabled effective understanding and generating complex programming codes. Consequently, they can help us in Data Security field. Let's see how!

[ NeurIPS 2023 R0-FoMo Workshop ] Official Codebase for "Estimating Uncertainty in Multimodal Foundation Models using Public Internet Data"

LLMs for Low Resource Languages in Multilingual, Multimodal and Dialectal Settings

PyTorch implementation of 'CLIP' (Radford et al., 2021) from scratch and training it on Flickr8k + Flickr30k

Diffusion Classifier leverages pretrained diffusion models to perform zero-shot classification without additional training

A minimal, but effective implementation of CLIP (Contrastive Language-Image Pretraining) in PyTorch

Interactive Reading Environment in Web-Based Virtual Reality (thesis project)