PyTorch Training by Markus Liedl

PyTorch is a great Deep Learning framework. It is dynamic and doesn't force you to describe the model statically. It's interactive nature and the great error messages help any deep learning beginner.

The PyTorch Training comprises two days in which you'll learn everything to use PyTorch productively:

• PyTorch tensors (views, memory sharing, subtensors, math, aggregations)
• fully connected layers and convolutional layers
• different non-linearities
• PyTorch autograd
• optimizing a model with the optim module (SGD, ADAM, ...)
• batch/weight/layer normalization and Why?
• running PyTorch networks on the GPU
• extend PyTorch with your own application specific modules
• improve a networks generalisation with dropout, noise, and appropriate data augmentations
• build upon finished PyTorch models from the model zoo
• lots of examples and exercises

The participants are expected to know Python language basics. The networks in the course target supervised learning for classification and regression.

If you are interested in the training mail me at markus.liedl.training@gmail.com Normally the training will happen in or near Munich, Germany. I'm also offering to join your team and work together with you on specific topics.

This course is available in English and German.

Related Deep Learning courses are

• Data augmentation course
• Generative Models course
• Torch training
• Reinforcement Learning Workshop