mintusf / land_cover_segmentation Goto Github PK
View Code? Open in Web Editor NEWSegmentation for land cover using raw satellite data (Sentinel 2La)
License: Apache License 2.0
Segmentation for land cover using raw satellite data (Sentinel 2La)
License: Apache License 2.0
Update README with:
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Describe this issue summary here.
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Update environment scripts
Update environment scripts
xx/xx
None
None
None
Add logger
Add logger
xx/xx
None
None
None
Describe this issue summary here.
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Describe this issue summary here.
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Add github actions
Add github actions
xx/xx
None
None
None
Add comet logging
Add comet logging
xx/xx
None
None
None
Describe this issue summary here.
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Add config
Add config
xx/xx
None
None
None
Describe this issue summary here.
None
None
Fix device selection
Fix device selection
xx/xx
None
None
None
Describe this issue summary here.
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
In order to make inference faster, we will convert to TensorRT
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Describe this issue summary here.
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Add focal loss
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Describe this issue summary here.
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Implement train and val step
Implement train and val step
xx/xx
None
None
In the dataset, there are for types of masks (as described here):
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Prepare train/val/test dataset split
Prepare lists for training
xx/xx
None
None
None
Describe this issue summary here.
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Describe this issue summary here.
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Currently it is done by notebook, but it is more convenient to implement it in the training pipeline.
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Add data augmentation
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Describe this issue summary here.
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Describe this issue summary here.
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Add recall, precision, confusion matrix
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Implement getters for:
Implement all getters
xx/xx
None
None
None
Describe this issue summary here.
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Implement training loop in order to train segmentation model.
None
None
If we keep appending targets and preds, GPU is out of memory.
In order to improve space complexity, let's calculate confusion matrix per batch and keep adding it to global confusion matrix.
After all batches are calculated, recall and precision can be calculated using only confusion matrix.
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Describe this issue summary here.
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Add device to config
Add device to config
xx/xx
None
None
Add pipenv env
Add pipenv env
xx/xx
None
None
None
The goal is to implement front end for querying and extracting satellite data using Sentinel API.
None
None
In order to load data, dataloader should be implemented.
It will load input data (satellite image), as well as ground truth (land cover segmentation).
Implement dataloader
xx/xx
None
None
None
In order to optimize predictions, we will make following updates to masks:
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Describe this issue summary here.
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
Describe this issue summary here.
Describe the definition by which this issue will be closed.
xx/xx
None
None
None
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.