Comments (2)
Hi,
The guidelines for adapting the pipeline for the COCO dataset are the following:
- Build the COCO loader that has the same methods and attributes as the VOC PASCAL one (dataset/voc_loader.py). It's best to build on top of pycocotools.
- Extract COCO instances into dedicated folders (analogous to the pascal)
- Train the context model on the coco dataset, perform inference to score the locations and perform location-instance matching (analogous to the pascal, described in the readme)
- Adapt context_aug/instance_manipulators.py to support COCO loader and to load instances from the dedicated folder. You will probably have to read instances from the disc each time you want to use one since all the coco instances won't fit into memory as opposed to PASCAL. For that, you will need to modify the init of the DynamicInstanceManipulator class.
This should be enough from what I recall.
Best
from context_aug.
Thank you very much. I'll try it .
from context_aug.
Related Issues (7)
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.
from context_aug.