Arbitrary Length Video Using Frame Chunking Based on official repository of code for "Towards An End-to-End Framework for Flow-Guided Video Inpainting" (CVPR2022)

Custom YoloV7 with vanilla tesseract OCR detection

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

TextBoxes: A Fast Text Detector with a Single Deep Neural Network

cliptrase

PyTorch Implementation of NACLIP in "Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation"

DataComp for Language Models

OpenVLA: An open-source vision-language-action model for robotic manipulation.

PTRAIL is a state-of-the art parallel computation library for Mobility Data Preprocessing and feature extraction.

Tensorflow implementation of the Social LSTM model

Pre-trained ELMo Representations for Many Languages

COCO-Text API http://vision.cornell.edu/se3/coco-text/

[CVPR'20] ZeroQ Mixed-Precision implementation (unofficial): A Novel Zero Shot Quantization Framework

ICLR 2021, Fair Mixup: Fairness via Interpolation

Code for "Localization with Sampling-Argmax", NeurIPS 2021

A Mesh-free Topology Optimization Method using Neural Representations

An open source implementation of CLIP.

DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

Object tracking implemented with the Roboflow Inference API, DeepSort, and OpenAI CLIP.

Model Reproduce Project for 616 CTRL GROUP, Department of Automation, Tsinghua University

Simple project base template for PyTorch deep Learning project. Features clean implementation of DDP training and Hydra config.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Contrastive Language-Image Pretraining

Ongoing research training transformer language models at scale, including: BERT & GPT-2

This is an official implementation for "Video Swin Transformers".

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Semantic Segmentation.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.