This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
object-detection
image-classification
semantic-segmentation
imagenet
swin-transformer
ade20k
mask-rcnn
mscoco
Обновлено 2024-07-15 18:00:32 +03:00
Experience, Learn and Code the latest breakthrough innovations with Microsoft AI
csharp
javascript
computer-vision
iot
bot
ai
object-detection
azure-functions
algorithms
dnn
luis
image-classification
bing-search
custom-vision
html5
language-learning
ocr
translation
Обновлено 2024-06-26 22:42:37 +03:00
Workshop for student hackathons focused on Lobe.ai
Обновлено 2024-01-09 08:40:23 +03:00
Best Practices, code samples, and documentation for Computer Vision.
microsoft
azure
machine-learning
python
deep-learning
data-science
computer-vision
kubernetes
artificial-intelligence
object-detection
tutorial
jupyter-notebook
convolutional-neural-networks
image-classification
image-processing
operationalization
similarity
Обновлено 2023-10-18 19:13:00 +03:00
Code for the neural architecture search methods contained in the paper Efficient Forward Neural Architecture Search
deep-learning
automl
neural-architecture-search
image-classification
cifar-100
cifar10
deep-learning-algorithms
imagenet
Обновлено 2023-06-12 21:22:32 +03:00
Deep Metric Transfer for Label Propagation with Limited Annotated Data
Обновлено 2023-06-03 07:09:23 +03:00
Intelligent APIs aim to make machine learning (ML) tasks easier for UWP developers to leverage in their applications without needing ML expertise or creating a new model.
Обновлено 2023-02-10 22:43:48 +03:00
This is an official implementation for "SimMIM: A Simple Framework for Masked Image Modeling".
Обновлено 2022-09-29 18:17:40 +03:00
Provably defending pretrained classifiers including the Azure, Google, AWS, and Clarifai APIs
machine-learning
deep-learning
computer-vision
neural-networks
image-classification
azure-computer-vision
clarifai
google-cloud-vision
provable-defense
adversarial-defense
adversarial-examples
adversarial-robustness
aws-rekognition
Обновлено 2021-04-03 00:37:13 +03:00
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
azure-storage
image-classification
neural-networks
cntk
microsoft-azure
land-cover
land-use
geospatial-data
image-segmentation
microsoft-machine-learning
azure-batchai
cntk-model
geospatial-analysis
Обновлено 2019-07-25 06:53:28 +03:00