Comments (1)
@Shuailong , thank you for your question. The reason for that was because i was using regression as a way to determine the correct class, rather than classification.
I have updated the code to reflect more of the classification style network where the output is now of the shape: (batch_size, num_labels)
from transformers-tutorials.
Related Issues (20)
- How to reload the model in a different machine with same hardware HOT 1
- Classifier ouput features are 4 in Model, then why this printed as 1? HOT 1
- T5 fine-tuning for summarization decoder_input_ids and labels HOT 3
- NER notebook issue HOT 1
- Colab Error :: RuntimeError: CUDA error: device-side assert triggered HOT 1
- Relation between transformers_multi_label_classification.ipynb and BertForMultipleChoice
- tokenizer = T5Tokenizer.from_pretrained("t5-base"). Type of tokenizer object is NoneType HOT 3
- problem on loading .bin model for inference HOT 1
- param of T5 model
- Tokenization issue in transformer NER HOT 4
- Saving the model
- T5 fine-tuning for summarization mistake
- Outputs are different when running the notebooks
- Variables not initialized in valid()
- Training based on Teacher forcing technique
- transformers_multi_label_classification.ipynb issue
- Where is train.csv?
- transformers_multi_label_classification.ipynb
- dataset split is invalid (because of reset_index) HOT 1
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 transformers-tutorials.