Light

epiphqny / solo Goto Github PK

View Code? Open in Web Editor NEW

164.0 8.0 17.0 9 MB

SOLO: Segmenting Objects by Locations

Python 83.87% C++ 5.22% Cuda 10.29% Shell 0.16% Cython 0.44%

instance-segmentation one-shot one-shot-instance-segmentation solo paper

solo's Introduction

👋 Hi, I’m Yuqing Wang, a PhD student in the University of Hong Kong.
👀 I’m interested in computer vision and generative models.
📫 How to reach me : [email protected].

solo's People

Contributors

Stargazers

Watchers

Forkers

chaoso jdc08161063 qgh1223 tiantianwang collector-m runzeer trendingtechnology anikily lliai trabish sjingwen ginobilinie lxcxuebao gaimjkp cv-ip y742035557 justimyhxu

solo's Issues

compile cu file

Could you please tell me how to compile .cu and .cpp file in mmdet/ops/xxx/src
I am not familiar with this
thanks

SOLOv1 on CPU supported?

How can I test this min version SOLO model on CPU?

Thanks

Seems official branch is not supported: WXinlong/SOLO#190 (comment)

where can I set batch_size?

I don't know much about mmdetection. where can I set batch_size in r50_p6.py?

Bug in Mask-NMS

There seems to be a bug in the below line.

SOLO/mmdet/models/anchor_heads/solo_head.py

Line 223 in 59a4c03

iou = float(overlap.sum())+1/(float(union.sum())+1)

Might it be the following line?

iou = float(overlap.sum() + 1) / float(union.sum() + 1)

And it might be faster to apply mask-nms on gpu.

About category target

Hi~ thanks for ur work
I notice that in ur implement, all grids touching gt center regions are sampled as positive

SOLO/mmdet/datasets/pipelines/transforms.py

Line 679 in 59a4c03

left_ = np.int(left[i]//w[j])

which is different from original paper 'grid (i, j) is considered as a positive sample if it falls into the center region of any ground truth mask'.
By my understanding, it's a positive sample as the grid center falls in center region.

Speed testing?

Did u compare the net forward speed compares to maskrcnn or other one-stage instance segmentation methods?

How are the values for H and W for the spatial resolution of the segmentation head selected? on both papers there is no exact description on that.

official implementation

check the official implementation here: https://github.com/WXinlong/SOLO

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.