Ghulam Jilani Raza's repositories
clip.cpp
CLIP inference in plain C/C++ with no extra dependencies
Pakistan-Residential-Electricity-Consumption
A repo to host analysis on PRECON dataset
cnos
[ICCV 2023 R6D] CNOS: A Strong Baseline for CAD-based Novel Object Segmentation based on Segmenting Anything and DINOv2
compute-engine
Highly optimized inference engine for Binarized Neural Networks
deep-image-matching
Multiview matching with deep-learning and hand-crafted local features for COLMAP. Supports high-resolution formats and images with rotations. Both CLI and GUI are supported.
deep-learning-explorations
an repo to host explorations and analysis on various aspects of deep learning
deepdetect
Deep Learning API and Server in C++14 support for Caffe, PyTorch,TensorRT, Dlib, NCNN, Tensorflow, XGBoost and TSNE
frigate
NVR with realtime local object detection for IP cameras
generative-models
Generative Models by Stability AI
go2rtc
Ultimate camera streaming application with support RTSP, RTMP, HTTP-FLV, WebRTC, MSE, HLS, MP4, MJPEG, HomeKit, FFmpeg, etc.
gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
hyena-dna
Official implementation for HyenaDNA, a long-range genomic foundation model built with Hyena
instruct-nerf2nerf
Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions (ICCV 2023)
kaggle-solutions
🏅 Collection of Kaggle Solutions and Ideas 🏅
ml-fastvit
This repository contains the official implementation of the research paper, "FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization" ICCV 2023
ml-upscale
Export utility for unconstrained channel pruned models
moondream
tiny vision language model
nougat
Implementation of Nougat Neural Optical Understanding for Academic Documents
prefect-runner-top-secret
Prefect is a workflow orchestration tool empowering developers to build, observe, and react to data pipelines
PUG
This is the repository for the Photorealistic Unreal Graphics (PUG) datasets for representation learning.
Robo3D
[ICCV'23] Robo3D: Towards Robust and Reliable 3D Perception against Corruptions
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
stable-diffusion.cpp
Stable Diffusion in pure C/C++
system-design-primer
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
tiny-dream
Tiny Dream - An embedded, Header Only, Stable Diffusion C++ implementation
Track-Anything
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.
Vim
Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model