Image Classification

Predict and classify the content of an image


How it Works

Draw the number indicated above the canvas using your mouse. A machine learning model is running “behind the scenes” to process your “handwriting” as an image and guess what number you’ve drawn. Since it isn’t possible to embed machine learning models directly into websites, the model is “hosted” on ScienceOps, where the website can “call” to it for its guess about what number you’ve drawn. ScienceOps can process hundreds of thousands of predictions per second.

Application Integration with ScienceOps

  • A trained Python model using the Keras library is deployed to ScienceOps
  • The model is integrated into a web application using the ScienceOps API
  • When you click draw an image, its POST'ed to the model API and predictions are returned

The Integration

curl -X POST --user username:1234567890abcdefg \
  --data '{"image_string": "iVBORw0KGElEQVR4Xu3dUZIUR9J"}' \
  https://sandbox.yhathq.com/demo/models/handwriting/
178   pca = RandomizedPCA(n_components=10)
179   std_scaler = StandardScaler()
180   X_train, X_test, y_train, y_test = train_test_split(data, labels, test_size=0.1)
181   ...
Checkout the rest of the code!
Contact
45 Main St #707,
Brooklyn, NY 11201
info@yhathq.com
+1 718 855 2107
+49 15735983455
Learn More
Connect With Us
Newsletter