Nima Dokoohaki's repositories
AAI_FY21_DataScience_Basics
AAI Sweden training FY21 - Data Science Basics
academic-kickstart
📝 Easily create a beautiful website using Academic, Hugo, and Netlify
ai-platform-samples
Official Repo for Google Cloud AI Platform
ASAM
Implementation of ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks, ICML 2021.
CADTransformer
[CVPR 2022]"CADTransformer: Panoptic Symbol Spotting Transformer for CAD Drawings", Zhiwen Fan, Tianlong Chen, Peihao Wang, Zhangyang Wang
Cutout
2.56%, 15.20%, 1.30% on CIFAR10, CIFAR100, and SVHN https://arxiv.org/abs/1708.04552
pytorch-retinanet
Pytorch implementation of RetinaNet object detection.
sam-pytorch
SAM: Sharpness-Aware Minimization (PyTorch)
Data-efficient-video-transformer
menovideo: pytorch library for video action recognition and video understanding
DfT-Road-Data-Accidents-Analytics
Exploratory analytics on UK DfT road data accidents
dotfiles
:wrench: .files, including ~/.macos — sensible hacker defaults for macOS
GiT
Official Implementation of "GiT: Towards Generalist Vision Transformer through Universal Language Interface"
Grounded-Segment-Anything
Grounded-SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
handson-ml
A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in python using Scikit-Learn and TensorFlow.
Image_manipulation_detection
Paper: CVPR2018, Learning Rich Features for Image Manipulation Detection
lightning-sam
Fine-tune Segment-Anything Model with Lightning Fabric.
mmaction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
notebooks
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.
OCR-SAM
Combining MMOCR with Segment Anything & Stable Diffusion. Automatically detect, recognize and segment text instances, with serval downstream tasks, e.g., Text Removal and Text Inpainting
panoptic-segment-anything
Combining Segment Anything (SAM) with Grounded DINO for zero-shot object detection and CLIPSeg for zero-shot segmentation
pytorch_DGCNN
PyTorch implementation of DGCNN
RGB-N
ResNetv1 trained on COCO
single-cell-experiments
Experiments to run single cell analyses efficiently at scale using Zarr, anndata, Scanpy, and Apache Spark
svhn-detection-tf
Object detection on SVHN dataset in tensorflow using efficientdet