asigalov61 / amazing-gpt2-piano Goto Github PK
View Code? Open in Web Editor NEWOpenAI's GPT2 based Music AI Google Colab Notebooks for Music Generation/Composition and Capabilities Evaluation
Home Page: https://openai.com/blog/musenet/
OpenAI's GPT2 based Music AI Google Colab Notebooks for Music Generation/Composition and Capabilities Evaluation
Home Page: https://openai.com/blog/musenet/
Hi
Five days ago worked well but today when I generate a midi get this error:
/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:61: TqdmDeprecationWarning: This function will be removed in tqdm==5.0.0
Please use tqdm.notebook.tqdm
instead of tqdm.tqdm_notebook
100%
3968/3968 [00:34<00:00, 115.93it/s]
ERROR:root:Internal Python error in the inspect module.
Below is the traceback from this internal error.
(1, 4096)
Successfully exported the output to output_file.mid
Downloading output_file.mid
Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py", line 2882, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "", line 196, in
files.download('/content/output-midis/output_file.mid')
File "/usr/local/lib/python3.6/dist-packages/google/colab/files.py", line 143, in download
raise FileNotFoundError(msg) # pylint: disable=undefined-variable
FileNotFoundError: Cannot find file: /content/output-midis/output_file.mid
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py", line 1823, in showtraceback
stb = value.render_traceback()
AttributeError: 'FileNotFoundError' object has no attribute 'render_traceback'
During handling of the above exception, another exception occurred:
Loss does not go down. I think it is a data problem.
Can someone help, please? :)
Hey guys,
If someone can help to improve or rewrite the encoder for this colab, I will really appreciate it.
I am training the model on my own MIDI set (~430) files. This way I can hear and experience over-fitting/plagiarism directly and precisely.
But it does not solve the issue of its existence. Should we just accept it? Or there is a good way to minimize it/prevent it?
Can someone recommend a code snippet perhaps? :)
Here is the error:
If someone can help, I will be grateful. Thank you.
Last line of code (lol)
midi.write_midifile("output.mid", pattern)
Produces:
AssertionError Traceback (most recent call last)
in ()
----> 1 midi.write_midifile("output.mid", pattern)
4 frames
/usr/local/lib/python3.6/dist-packages/midi/fileio.py in write_midifile(midifile, pattern)
167 if type(midifile) in (str, str):
168 with open(midifile, 'wb') as out:
--> 169 return write_midifile(out,pattern)
170 writer = FileWriter(midifile)
171 return writer.write(pattern)
/usr/local/lib/python3.6/dist-packages/midi/fileio.py in write_midifile(midifile, pattern)
169 return write_midifile(out,pattern)
170 writer = FileWriter(midifile)
--> 171 return writer.write(pattern)
172
173 def read_midifile(midifile):
/usr/local/lib/python3.6/dist-packages/midi/fileio.py in write(self, pattern)
103 self.write_file_header(pattern,len(pattern))
104 for track in pattern:
--> 105 self.write_track(track)
106
107 def write_file_header(self, pattern, length=None):
/usr/local/lib/python3.6/dist-packages/midi/fileio.py in write_track(self, track)
120 buf = bytearray(b'0'*hlen)
121 for event in track:
--> 122 buf.extend(self.encode_midi_event(event))
123 buf[:hlen] = self.encode_track_header(len(buf)-hlen)
124 self.file.write(buf)
/usr/local/lib/python3.6/dist-packages/midi/fileio.py in encode_midi_event(self, event)
139 ret = bytearray()
140 #assert hasattr(event,'tick'), event
--> 141 assert isinstance(event.tick,int), event.tick
142 ret.extend(write_varlen(event.tick))
143 # is the event a MetaEvent?
AssertionError: 20
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.