StepCOVNet
StepCOVNet copied to clipboard
Deep Learning to Create StepMania SM FIles
Thought I'd try to test this project out. Being on Windows + Lack of windows tensorflow support has made it a challenge. Using WSL2, I've managed to get far enough...
Or is it designed to just automatically determine the difficulty based on the audio provided?
https://www.tensorflow.org/io/tutorials/audio
Some of the raw training data found in the Google Drive doesn't contain the audio files corresponding to them (e.g. bluhende_nacht.ogg).
On latest version when I try run stepmania_note_generator.py I get the following: ``` PS C:\dev\StepCOVNet-master> python stepmania_note_generator.py -i test_in -o test_out --model dataset\time2_challenge_timing_model -v 1 Loading StepCOVNet retrained model Failed...
1. https://github.com/marketplace/actions/todo-to-issue 2. https://github.com/marketplace/actions/todo-actions
This can come in the form of a Google sheets that has the name of the song and metadata about it.
In general, it'll be better for ease of use and visibility for hyperparameters to be moved into a config file that's read by `train.py.` After the move, the config options...