How do I in Python

• Express things
• Train models
• Interpret the use of MinibatchSource.next_minibatch?
• Load pre-trained checkpointed model and continue retraining?
• Relate alpha, beta1, beta2 and epsilon to learning rate and momentum in adam_sgd?
• Train two or more models jointly?
• Train with a weighted loss?
• Train a multilabel classifier in Python?
• Train an Image auto encoder using Deconvolution and Unpooling?
• Object Detection using Fast R-CNN
• Build your own image classifier using Transfer Learning

Evaluate models

• Evaluate a saved convolutional network?
• Extract features from a specific layer using a trained model?

Adapt models

• Read and modify the training weights from Python?

Read things

• Load model and access network weights / parameters?

Deal with errors

• Debug a Python notebook?
• Get things to work correctly when I take the last element of a sequence?