Microsoft Vision Transfer Learning

Introduction

Microsoft Vision Model

Credits — Microsoft Research Blog
  1. ImageNet-22k,
  2. Microsoft COCO, and
  3. Two Web-supervised datasets (containing 40 million image-label pairs collected from image search engines)

Using Microsoft vision

pip install microsoftvision

Use of Microsoft vision for transfer learning

Flow diagram for Transfer Learning with Microsoft Vision

Preprocessing

  1. The input images have to be in the BGR format which has the shape of (3 X H X W), where the H — height and W — Width is recommended to be 224 X 224.
  2. The images have to be normalized to have a value between 0 and 1 using the
    a. mean = [0.485, 0.456, 0.406]
    b. Std = [0.299, 0.224, 0.255]

Transfer learning

Transfer Learning

Vision Model as Feature Extractor

Implementation

References

  1. Microsoft Research Blog
  2. Github
  3. https://github.com/abhi-gm/Microsoft-Vision-Transfer-Learning
  4. Data — 10.17632/rp73yg93n8.1#file-56487963–3773–495e-a4fc-c1862b6daf91

--

--

--

Data Scientist | ML-Ops| https://abhi-gm.github.io/ | https://www.linkedin.com/in/abhishek-g-m/ | https://github.com/abhi-gm

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

How to build a self-driving car in two days and learn about deep learning

Get better depth from monocular images by using segmentation masks with MaskDepth

What is Ensemble Learning?

Feature Selection Techniques in Machine Learning

Time-series forecasting using ordinary Machine Learning algorithms

AI for revenue growth: using ML to drive more valuable pricing

KNN_DecisionTree_RandomForest_SVM_ANN_GridSearchCV_SMOTE_XGBoost

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Abhishek Maheshwarappa

Abhishek Maheshwarappa

Data Scientist | ML-Ops| https://abhi-gm.github.io/ | https://www.linkedin.com/in/abhishek-g-m/ | https://github.com/abhi-gm

More from Medium

Prototyping of image inpainting methods using attention and normalizing flows

CV Series 4— Image Formation Part 3 (Theory)

Training a Computer Vision Model on VertexAI (with and without Explanable option)

Studying Cross Transferability of Vision Transformers using HAM10000 skin cancer dataset