Machine Learning and Physics, Sheet 10

Setup

For this sheet we set up a new conda environment, that includes ffmpeg and celluloid. Alternatively, install these packages in the environment of the last sheet, or upload the notebook to google colabe (then you can even use the GPU for training)

Clone this repo and navigate into it:

git clone https://github.com/hci-unihd/mlph_sheet10.git
cd mlph_sheet10

Install and activate the conda environment:

conda env create --file=environment.yml
conda activate mlph4

Then you can start jupyter (run jupyter notebook) and open sheet10.ipynb, which you should use as the basis for the solution of the practical excercises.

Hand in

Hand in both your jupyter notebook, and an exported pdf (File -> Download as -> pdf). If you encounter problems exporting the pdf like this, please print your notebook to pdf and hand this in.