twangnh Goto Github PK

aggmask-1

Anonymous repository containing the code of the AggMask

cocostuff

The official homepage of the COCO-Stuff dataset.

crat

deformable-detr

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

detectron2

Detectron2 is FAIR's next-generation platform for object detection and segmentation.

detr-1

End-to-End Object Detection with Transformers

distilling-object-detectors

Implementation of CVPR 2019 paper: Distilling Object Detectors with Fine-grained Feature Imitation

distilling-object-detectors-shuffledet

Implementations of CVPR 2019 paper Distilling Object Detectors with Fine-grained Feature Imitation

epipolar-transformers

Epipolar Transformers (CVPR 2020)

glore

Global Reasoning module for visual recognition

linear-multihead-attention

Reproducing the Linear Multihead Attention introduced in Linformer paper (Linformer: Self-Attention with Linear Complexity)

lvis-for-mmdetection

support Large Vocabulary Instance Segmentation (LVIS) dataset for mmdetection

mask3d-shift

This repository provides a multi task benchmark for instance segmentation, depth estimation, and 3D object detection.

pnp-detr

Implementation of ICCV21 paper: PnP-DETR: Towards Efficient Visual Analysis with Transformers

poll-and-pool

Code of ICCV paper: PnP-DETR: Towards Efficient Visual Analysis with Transformers

psroialign-multi-batch-pytorch

PSROIAlign with multi-batch training support in PyTorch

pytorchtricks

Some tricks of pytorch... :star:

releasing-research-code

Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)

shufflenet-prototxt-generator

This repository implements a ShuffleNet prototxt generator and a more efficient channel shuffle implementation

simcal

Implementation of ECCV20 paper: the devil is in classification: a simple framework for long-tail object detection and instance segmentation

solo-1

SOLO: Segmenting Objects by Locations https://arxiv.org/abs/1912.04488

solov2

SOLOv2: Dynamic, Faster and Stronger, achives 39.5mAP on coco test-dev (36 epochs result)

torchprof

PyTorch layer-by-layer model profiler

twangnh.github.io

volo

VOLO: Vision Outlooker for Visual Recognition