#
microsoft-machine-learning
Here are 7 public repositories matching this topic...
Tutorial demonstrating how to create a semantic segmentation (pixel-level classification) model to predict land cover from aerial imagery. This model can be used to identify newly developed or flooded land. Uses ground-truth labels and processed NAIP imagery provided by the Chesapeake Conservancy.
microsoft
cntk
geospatial-data
neural-networks
image-classification
image-segmentation
azure-storage
land-cover
land-use
geospatial-analysis
microsoft-azure
microsoft-machine-learning
cntk-model
azure-batchai
-
Updated
Jul 25, 2019 - Jupyter Notebook
An unofficial Microsoft Machine Learning Server Docker image.
microsoft
docker
machine-learning
docker-image
microsoftml
microsoft-machine-learning
microsoft-machine-learning-server
-
Updated
Oct 6, 2017
Re-implementation and extension of the work described in "Learning to Represent Programs with Graphs"
microsoft
machine-learning
graphs
vocabulary
corpus
inference
yml
microsoft-machine-learning
microsoft-research
gnns
graph-neural-networks
dataset-parsing
checkpoint-path
corpus-extractor
variable-naming
ml-programming
programming-ml
-
Updated
May 14, 2019 - Python
A web mapping app to test, tweak and train the land cover classification from a deep neural network model built by @microsoft
image-classification
arcgis-js-api
land-cover
microsoft-azure
microsoft-machine-learning
ai-for-earth
-
Updated
May 24, 2018 - JavaScript
A collection of Microsoft ML experiment Jupyter notebooks.
machine-learning
jupyter-notebook
microsoftml
microsoft-machine-learning
microsoft-machine-learning-server
-
Updated
Oct 20, 2017 - Jupyter Notebook
Machine learning projects implemented by ML.NET using F#
-
Updated
Jun 6, 2018 - F#
Improve this page
Add a description, image, and links to the microsoft-machine-learning topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the microsoft-machine-learning topic, visit your repo's landing page and select "manage topics."
I have a simple regression task (using a LightGBMRegressor) where I want to penalize negative predictions more than positive ones. Is there a way to achieve this with the default regression LightGBM objectives (see https://lightgbm.readthedocs.io/en/latest/Parameters.html)? If not, is it somehow possible to define (many example for default LightGBM model) and pass a custom regression objective?