Comments (4)
hi @cyl250
It is common to combine features by simply concatenate them (along the feature dimension).
The CPC feature is [num_framess, 256] and MFCC is [num_frames, 39]. Concatenating them would give [num_frames, 256+39].
from contrastive-predictive-coding-pytorch.
sorry, I have some trouble to understant
After model.predict() the CPC features is in [128,256] dims.
Do I need change the numbers of node of network to fix mode.prdict() return a [num_frames,256] vectors?
from contrastive-predictive-coding-pytorch.
128 is the number of frames during TRAINING. In the CPC training, random chunks from the raw waveform are selected and input to the encoder. For example, a random chunk of 20480 data points corresponds to 1.28 seconds, or 128 frames (16k Hz audio).
During inference, you should input the entire utterance instead of the chunks. This will give you the correct number of frames instead of 128.
from contrastive-predictive-coding-pytorch.
from contrastive-predictive-coding-pytorch.
Related Issues (20)
- Train and test data not available HOT 1
- why torch.diag in nce loss?
- Train the spk_class.py
- the self.softmax() don't update the paras in the CDCK2? HOT 1
- NCE accuracy calculation HOT 1
- Hey should 'correct' only be if the final prediction was correct? Same for accuracy? HOT 1
- About negative sample?
- Feed entire input to encoder?? HOT 1
- Second last tilmestep as the c_t in the baseline model?
- Softmax uses by default dimension 1
- Code question in src/model/model.py#L113 HOT 1
- Use of Batch Normalisation
- NCE should be calculated for each output of the GRU (and future positions) instead of only a random index
- May I ask which version of torch do you use? HOT 2
- Some Trouble in Understanding HOT 5
- Threre might some wrong in validation.py HOT 1
- The implementation of loss might be wrong HOT 1
- how to format h5 files for input? HOT 3
- What is the format of "list" file? HOT 2
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 contrastive-predictive-coding-pytorch.