Open machakw21 opened 4 years ago
I have a similar problem!
I just run without changing any {Filename}
Generating level for Some_Things_Never_Change_From_Frozen_2_Lyric_Video.mp3
mkdir: cannot create directory ‘generated’: File exists
Traceback (most recent call last):
File "generate_stage1.py", line 72, in
Please advise on any chnages to code to get this working
Hi, sorry for late reply
@machakw21 , thanks for the report. I think it was a problem with an pudate in pytorch. I think I've fixed it now. Can you try again?
@Kowleone Did you run the cell titled "Prepare deepsaber and dependencies" ? If it still doesn't work try opening the page again, change the deepsaber_folder_name
and run the cells, so that it would download deepsaber from scratch again.
Having a similar issue of sorts, granted, really new to this and I am unsure what I may be doing wrong but so far it will not let me get past the first step of downloading songs from YouTube to use for this.
download_from_youtube = True #@param {type:"boolean"} youtube_url = 'https://www.youtube.com/watch?v=BNXKppay2j0' #@param {type:"string"} if download_from_youtube: !export youtube_url !youtube-dl -x --audio-format mp3 --restrict-filenames $youtube_url filename=!youtube-dl -x --audio-format mp3 --get-filename --restrict-filenames $youtube_url filename = os.path.splitext(filename[0])[0]+".mp3" filename_new = filename[:50]+".mp3" !mv $filename songs/$filename_new filename = filename_new else: res=files.upload() filename=list(res.keys())[0] os.rename(filename,"songs/"+filename)
I have tried running this by pulling the song from youtube and a copy I have, I get the same error.
Generating level for Diesel_Not_Petrol.mp3 Traceback (most recent call last): File "generate_stage1.py", line 94, in
first_samples = torch.full((1,opt.output_channels,receptive_field//2),constants.START_STATE)
RuntimeError: Providing a bool or integral fill value without setting the optional
dtype
orout
arguments is currently unsupported. In PyTorch 1.7, whendtype
andout
are not set a bool fill value will return a tensor of torch.bool dtype, and an integral fill value will return a tensor of torch.long dtype. usage: generate_stage2.py [-h] [--song_path SONG_PATH] [--json_file JSON_FILE] [--experiment_name EXPERIMENT_NAME] [--checkpoint CHECKPOINT] [--temperature TEMPERATURE] [--bpm BPM] [--generate_full_song] [--use_beam_search] [--open_in_browser] [--cuda] generate_stage2.py: error: unrecognized arguments: the model from ../../scripts/training/block_placement_ddc2/iter_130000net.pthIndexError Traceback (most recent call last)