ghljh Goto Github PK

secant

[ICML 2021] Official code for SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies

segment-everything-everywhere-all-at-once

Official implementation of the paper "Segment Everything Everywhere All at Once"

senet

Squeeze-and-Excitation Networks

sfanet-crowd-counting

This is an unofficial implement of the arXiv paper Dual Path Multi-Scale Fusion Networks with Attention for Crowd Counting by PyTorch.

sg-epunet

shapeprop

Learning Saliency Propagation for Semi-supervised Instance Segmentation

simcal

simclr

SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners

sipmask

SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation (ECCV2020)

snake

Code for "Deep Snake for Real-Time Instance Segmentation" CVPR 2020 oral

stem-seg

This repository contains the official implementation of the paper "STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos"

stn-spatial-transformer-network

A Tensorflow implementation of Spatial Transformer Networks

stylegan2-pytorch

Implementation of Analyzing and Improving the Image Quality of StyleGAN (StyleGAN 2) in PyTorch

swin-transformer

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

tbbrdet

Thermal Bridges on Building Rooftops Detection (TBBRDet)

tensorflow

Computation using data flow graphs for scalable machine learning

tensormask-review

Sliding-window object detectors that generate boundingbox object predictions over a dense, regular grid have advanced rapidly and proven popular. In contrast, modern instance segmentation approaches are dominated by methods that first detect object bounding boxes, and then crop and segment these regions, as popularized by Mask R-CNN. In this work, we investigate the paradigm of dense slidingwindow instance segmentation, which is surprisingly underexplored. Our core observation is that this task is fundamentally different than other dense prediction tasks such as semantic segmentation or bounding-box object detection, as the output at every spatial location is itself a geometric structure with its own spatial dimensions. To formalize this, we treat dense instance segmentation as a prediction task over 4D tensors and present a general framework called TensorMask that explicitly captures this geometry and enables novel operators on 4D tensors. We demonstrate that the tensor view leads to large gains over baselines that ignore this structure, and leads to results comparable to Mask R-CNN. These promising results suggest that TensorMask can serve as a foundation for novel advances in dense mask prediction and a more complete understanding of the task. Code will be made available.

tpu

Reference models and tools for Cloud TPUs.

usbuildingfootprints

Computer generated building footprints for the United States

val3dity

Validation of 3D primitives according to the international standard ISO19107

visgraph

vision_transformer

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

vit-tensorflow

Vision Transformer Cookbook with Tensorflow

vit-vision_transformer

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

white-jotter

白卷是一款使用 Vue+Spring Boot 开发的前后端分离项目，附带全套开发教程。（A simple CMS developed by Spring Boot and Vue.js with development tutorials）

yolov5

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

yolov7

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