Comments (6)
Granted, I am having this problem with version 3.5.0, thought perhaps issue might have been the same. I saw it, and tried it, but sadly to no avail. The default values of these parameters seem to match. I tried to match them manually in the notebook as well as changing them in both place to these values in your example, but still getting the same frame_size vs. hop_size error.
from ddsp.
I have the same exact problem.
I´m trying to run it locally, and I honestly dont know how it still runs in collab but it crashes here, with the same values.
I tried increasing the frame size to 512 and 320 (just to see if it works) and then I get another error:
File "...\ddsp\training\postprocessing.py", line 330, in get_stats max_list.append(np.max(x_i[m])) IndexError: boolean index did not match indexed array along dimension 0; dimension is 181 but corresponding boolean dimension is 980
I´m not that thrilled to see that this happened to you in March and there´s still no replys too.
from ddsp.
I just tried the same thing locally and I'm getting the same error.
from ddsp.
@sharp-trickster @theloni-monk I'm no longer working on this, but if I recall correctly the issue is the the TFRecordProvider
must be initialized with the exact same arguments that the dataset was created with in ddsp_prepare_tfrecord
, otherwise you get mysterious errors like this. For example,
data_provider = ddsp.training.data.TFRecordProvider(
args.train_tfrecord_filepattern,
# Make sure these arguments match what the dataset was created with!
# sample_rate=44100,
frame_rate=50,
centered=True,
with_jukebox=False,
)
Look for ddsp_prepare_tfrecord.py
to see what the defaults are.
See also the updated script I made for my thesis.
from ddsp.
Anybody ever solved this?
from ddsp.
@olaviinha see my comment above, it's about the arguments to the TFRecordProvider
not matching what the data was created with. The frame_rate
and centered
arguments must match, otherwise you get mysterious errors like this.
from ddsp.
Related Issues (20)
- DDSP in Docker Container HOT 7
- ValueError: Size of each quantile / not able to compute features in timbre_transfer
- DDSP Colab Notebook - Pip Install is not worked HOT 12
- "NotImplementedError" HOT 1
- AttributeError HOT 1
- Harmonic component not getting trained while training on a higher sample rate!
- NotImplementedError while trying to run training HOT 2
- DDSP VST Model training & autoencoder training both instantly start to slow down significantly
- Here's an example to transfer timbre in browser [Docs]
- Plugin not appearing in Ableton Live (Macbook pro M1) HOT 1
- Train VST Colab shows as idle when training
- TrainVST colab shows as idle when training
- Any chance to get the colab demo working again? HOT 2
- Possible to use VST model programmatically? HOT 1
- OnlineF0PowerPreprocessor cannot function with compute_power = False.
- No module crepe
- AttributeError: module 'hmmlearn.hmm' has no attribute 'CategoricalHMM'
- AttributeError: module 'hmmlearn.hmm' has no attribute 'CategoricalHMM'
- AttributeError: module 'hmmlearn.hmm' has no attribute 'CategoricalHMM'
- AttributeError: module 'collections' has no attribute 'Iterable'
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 ddsp.