developmentseed / developmentseed/ml-enabler
Training Data Visualization
- 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