Comments (4)
Hi @NotNANtoN !
Thank you for your accurate observation. At some point, I changed the BCELoss to BCEWithLogitsLoss (removing an nn.Sigmoid() call) for the training scheme, but missed adding a sigmoid operation during evaluation. I will report back the results to you, thank you!
from clmr.
This changes results for a linear classifier from the reported:
ROC-AUC_tag = 88.49
PR-AUC_tag = 35.37
To:
ROC-AUC_tag = 88.73
PR-AUC_tag = 35.58
from clmr.
And it changes results for a 2-layer multi-layer perceptron from the reported:
ROC-AUC_tag = 89.3
PR-AUC_tag = 35.9
To:
ROC-AUC_tag = 89.3
PR-AUC_tag = 36.0
(the values obtained in recent commits are a bit lower because they indeed uses .softmax instead of .sigmoid for multi-label datasets)
from clmr.
Thanks again for your accurate observation! I hope our work has been useful to you :)
from clmr.
Related Issues (20)
- Is there any length limit of the music with this method? HOT 1
- ValueError: The `target` has to be an integer tensor. HOT 2
- About the experiment results: different methods' songs' length? HOT 1
- t-sne visualization
- PyTorch Lightning version HOT 2
- Weights for million song dataset? HOT 3
- Train / Validation / Test splits for million song dataset HOT 9
- colab installation broken (dependencies) HOT 1
- moules.linear_evaluation is missing parameters when calling Accuracy and AveragePrecision
- Where is 'processed_annotations' for Million Song Dataset? HOT 2
- million song dataset
- Extracting embeddings?
- Does this project only run on linux platform?
- train by raw dataset HOT 1
- config for reproducing the provided model clmr_checkpoint_10000.pt HOT 1
- RuntimeError: Sizes of tensors must match except in dimension 0. Got 59049 and 1 in dimension 1 (The offending index is 1) HOT 1
- How much loss does the model converge
- the pretrained model on GTZAN HOT 1
- Import Error in colab 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 clmr.