Comments (3)
Was the new top-level prior trained without labels? If it was trained with no labels, you want to pass labels=False in the small_prior hps too, as it seems the model is trying to make a labeller object when it shouldn't.
Note you'll still need to pass an (artist, genre) label while using the upsampling levels, though it should be fine to use (0,0) ie (unknown, unknown) for those as the upsampling doesn't depend too strongly on the labels.
from jukebox.
The small_prior only provides a base set of values to start from, you want to add specific values for labels, t_ranges etc for the model you trained when you load it. Might be easier to get them directly from the saved checkpoint, since that saves the hps too.
from jukebox.
I was trying the same, added "labels=False" in params.py for small_vqvae, small_prior and small_upsampler but got stuck:
/jukebox# python jukebox/sample.py --model=my_model --name=sample_my_model --levels=3 --sample_length_in_seconds=20 --tot
al_sample_length_in_seconds=180 --sr=44100 --n_samples=6 --hop_fraction=0.5,0.5,0.125
Using cuda True
{'name': 'sample_my_model', 'levels': 3, 'sample_length_in_seconds': 20, 'total_sample_length_in_seconds': 180, 'sr': 44100, 'n_sample
s': 6, 'hop_fraction': (0.5, 0.5, 0.125)}
Setting sample length to 440832 (i.e. 19.99238095238095 seconds) to be multiple of 256
0: Loading vqvae in eval mode
Conditioning on 1 above level(s)
Checkpointing convs
Level:0, Cond downsample:2, Raw to tokens:2, Sample length:16384
0: Loading prior in eval mode
Conditioning on 1 above level(s)
Level:0, Cond downsample:2, Raw to tokens:2, Sample length:16384
0: Loading prior in eval mode
Traceback (most recent call last):
File "jukebox/sample.py", line 275, in <module>
fire.Fire(run)
File "/opt/miniconda/lib/python3.7/site-packages/fire/core.py", line 127, in Fire
component_trace = _Fire(component, args, context, name)
File "/opt/miniconda/lib/python3.7/site-packages/fire/core.py", line 366, in _Fire
component, remaining_args)
File "/opt/miniconda/lib/python3.7/site-packages/fire/core.py", line 542, in _CallCallable
result = fn(*varargs, **kwargs)
File "jukebox/sample.py", line 272, in run
save_samples(model, device, hps, sample_hps)
File "jukebox/sample.py", line 223, in save_samples
labels = [prior.labeller.get_batch_labels(metas, 'cuda') for prior in priors ]
File "jukebox/sample.py", line 223, in <listcomp>
labels = [prior.labeller.get_batch_labels(metas, 'cuda') for prior in priors ]
File "/opt/miniconda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 576, in __getattr__
type(self).__name__, name))
AttributeError: 'SimplePrior' object has no attribute 'labeller'
/jukebox#
How can I avoid this?
from jukebox.
Related Issues (20)
- Installation Error,Packages not found HOT 7
- Fine-tuning the prior
- Hudba
- Error
- Just ignore
- Error right at the start of Colab HOT 1
- Changing output permissions
- stuck repeating the last few lines over and over and over and over again
- #0penA1 - #Fu11A1
- Encountering Errors with OpenAI Jukebox in Google Colab HOT 3
- Enhancement feature
- "Installation Error: jukebox package not found on conda channels (Windows 64-bit, Python 3.9.18)" "Unable to Install Jukebox from Conda (conda 23.11.0, Python 3.9.18)" HOT 1
- Syntax error on Colab
- My trackq HOT 1
- Rt
- Te amo
- AROA HOT 1
- Size mismatch
- Ya par tal
- Does anyone use the jukebox on their mac M2?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from jukebox.