Comments (2)
It was a bug. It was expected that the batch size would always be equal to the default value (i.e. 64) while some batches (especially the last of each epoch) might not contain that number of examples.
I just committed a bug fix.
Could you confirm that it solved your problem?
Bests
Danilo
from ganbert-pytorch.
print(log_probs.shape)
--->torch.Size([64, 19])
print(label2one_hot.shape)
--->torch.Size([63, 19])
from ganbert-pytorch.
Related Issues (20)
- Number of discriminator output HOT 1
- Is it possible to obtain the text representation generated fake examples? HOT 1
- how do we use the trained model HOT 1
- Support for validation set instead of evaluating on test set directly. HOT 3
- Is the number of unlabeled examples related to the model accuracy? HOT 1
- Train Accuracy in evaluation mode is decreased by every epoch HOT 1
- Generator doesn't work HOT 2
- Gan BERT for Multilabel Intent Classification HOT 1
- Unable to reproduce the results for 20-News dataset HOT 2
- Saving Best model during training
- Deploy the model to use with live data
- Normal distibution HOT 1
- Electra support HOT 2
- Feature matching loss HOT 1
- Accuracy problem HOT 1
- do you have tensorflow code?thankyou HOT 1
- Save and deploy Model HOT 1
- How to show some illustration after complete train model ? HOT 3
- Calculate F1 HOT 3
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 ganbert-pytorch.