MP5: Video synthesis using LSTM

In this MP, you will use an LSTM to synthesize short video sequences.

In this MP, you will use a hidden Markov model to segment the phonemes in a speech database.

  • mp5.zip contains the code. You should download the code, unzip it into some directory, and then type jupyter-lab to get started.

  • mp5_notebook.html is example of what the Jupyter notebook will look like, once you’ve finished everything.

  • python run_tests.py is how you will grade your code on your local machine. The solutions are available to you in solutions.hdf5.

  • When it works on your machine, then you can try uploading only the file submitted.py to the MP5 assignment on Gradescope.

Extra Credit

  • The extra credit assignment is included as part of mp5.zip. This adds one more file for you to work on (extra.py), and one more visible test file (tests/test_extra.py).

  • When you’ve finished revising extra.py, you can test it on your machine by running python grade.py.

  • When it works on your machine, upload only the file extra.py to the MP5 Extra assignment on Gradescope.