Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit
-
Updated
Sep 8, 2020 - C++
{{ message }}
Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit
Set up deep learning environment in a single command line.
MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.
Visual Object Tagging Tool: An electron app for building end to end Object Detection Models from Images and Videos.
Scenarios, tutorials and demos for Autonomous Driving
GPU-accelerated Deep Learning on Windows 10 native
Keras package for region-based convolutional neural networks (RCNNs)
Continuous Machine Learning Training and Deployment on AWS SageMaker
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.
ANNdotNET - deep learning tool on .NET Platform.
Deep Learning with C# and CNTK
The On-Ramp to Deep Learning
A Deep Learning talk+tutorial for medical image processing
We provide GPU-enabled docker images including Keras, TensorFlow, CNTK, MXNET and Theano.
Bounding box detection of drones (small scale quadcopters) with CNTK Fast R-CNN
A workbench for online model-free Reinforcement Learning on continuous control problems
Machine Comprehension Train on MSMARCO with S-NET Extraction Modification
This POC is using CNTK 2.1 to train model for multiclass classification of images. Our model is able to recognize specific objects (i.e. toilet, tap, sink, bed, lamp, pillow) connected with picture types we are looking for. It plays a big role in a process which will be used to classify pictures from different hotels and determine whether it's a picture of bathroom, bedroom, hotel front, swimming pool, bar, etc.
This sample project shows off how to prepare and deploy to Azure Web Apps a simple Python web service with an image classifying model produced in CNTK (Cognitive Toolkit) using FasterRCNN
Prometheus is a machine learning powered solution for early detection of fires in national parks
A playground for continual, interactive neuroevolution
Some Deep learning tools in Unity using CNTK
A Docker container with Azure Resource Manager administration tools and a machine/deep learning stack
A python implementation for a CNTK Fast-RCNN evaluation client
Deep learning library that builds on and extends Microsoft CNTK
Deep Learning (Keras) Models Deployment using SQL databases
Add a description, image, and links to the cntk topic page so that developers can more easily learn about it.
To associate your repository with the cntk 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?