developmentseed / developmentseed/ml-enabler

Training Data Visualization

Open
#5 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
JavaScript
Stars
30
Forks
2
PR merge metrics
No merged PRs in 30d

Description

With PR developmentseed/ml-enabler#98 (TF-Record Creation), ML-Enabler will be able to create initial model training data tf-records for a user assuming the user provides a vector of geojson data + imagery.

It would be a nice enhancement to visualize the training data, in a similar manner to how ML-Enabler already has the UI in place to visualize predictions.

It would also be great to be able to visually look at the train, test, and validation split and have those color-coded when the training data is displayed over the imagery on the map.

cc @ingalls

Contributor guide

No contributing guide indexed for this repository

Research direction

The issue names no files or tests; start by locating the existing prediction-visualization UI and reviewing PR developmentseed/ml-enabler#98 for the training-data format. Done means displaying training data over imagery on the map and visually distinguishing the train, test, and validation splits with different colors.

Written by the indexing model from the issue text.

Assessment

Tech stack
javascript
Domain
data-visualization, frontend, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.