Here we collect a series of notebooks to familiarize with some important data processing and analysis pipelines based on PyTorch (https://pytorch.org/).

• Notebook_1.ipynb : Fundamentals
• Notebook_2.ipynb : Gradients, Optimizers and Loss Functions
• Notebook_3.ipynb : Standard workflow and Linear Regression
• Notebook_4.ipynb : Standard workflow and Logistic Regression
• Notebook_5.ipynb : Multiclass classification
• Notebook_6.ipynb : Neural Networks, Activation Functions and Digit Recognition
• Notebook_7.ipynb : Recurrent Neural Networks and Name Classification
• helper_functions.py: Auxiliary functions needed in some of the previous notebooks

To do:

• Notebook_8 : Convolutional Neural Networks and Computer Vision
• Notebook_9 : Application of Convolutional Neural Networks to an Image Recognition problem
• Notebook_10 : Modularity and Transfer Learning
• Notebook_11 : Application of Transfer Learning to a Computer Vision problem
• Notebook_12 : Experiment tracking

All the datasets used are the standard ones available in PyTorch or in Scikit-Learn. The only exception is Notebook 7 wich uses custom data that can be found in the zipped folder data.zip.