No content

No content

Classification – Using a model KNeighborsClassifier(algorithm='auto’, leaf_size=30, metric='minkowski', metric_params=None, n_jobs=1, n_neighbors=3, p=2, weights='uniform') By Antti Ajanki AnAj - Own work, CC BY-SA 3.0, https://commons.wikimedia.org/w/index.php?curid=2170282 

Classification – Using a model classify: Composite(Tensor[3,128,128]) -> Tensor[2] https://cntk.ai/pythondocs/CNTK_103D_MNIST_ConvolutionalNeuralNetwork.html (3,128,128) (2) 0.14 

CNN - Convolution 

CNN – Max Pooling • Reduce dimensionality (Speed up the network) • More tolerant to object location changes 

No content

• • • • • • • 

pred_label = model.predict(arr.flatten()) pred_prob = model.predict_proba(arr.flatten()) index = np.where(model.classes_ == pred_label) return ( pred_label[0], pred_prob[0][index][0] ) predictions = model.eval(arr)[0] top_class = np.argmax(predictions) lables = ['croissant', 'sloth’] return ( lables[top_class], predictions[top_class] ) 

Deployment – Docker https://aka.ms/flask-ml 

No content

Resources https://github.com/starlord-daniel/flask-rest/tree/ml-endpoint https://azure.microsoft.com/en-us/services/container-service/ http://scikit-learn.org/stable/tutorial/basic/tutorial.html https://github.com/Microsoft/botbuilder-python https://cntk.ai/pythondocs/CNTK_103D_MNIST_ConvolutionalNeuralNetwork.html 

aka.ms/dheinze for info || aka.ms/dheinze-py for script { "About me": { "Name": "Daniel Heinze", "Mail": "[email protected]", "Description": "Software Developer since 2006", "Twitter": "@starlord_daniel", "Facebook": "danielsdevblog", "Github": "https://github.com/starlord-daniel" } }