dalisson/am_softmax
This is a pytorch implementation of the am_softmax, this softmax layer includes the class assignment fully connected layer, as it is required for it to be normalized.
This tool helps improve the quality of 'embeddings' — numerical representations of complex data like images or text — so that similar items are grouped more closely together and different items are pushed further apart. If you're building a system that needs to accurately classify or recognize patterns within your data, this can enhance its performance. It takes a batch of these data embeddings and outputs scores indicating class likelihood.
No commits in the last 6 months.
Use this if you are developing machine learning models for tasks like facial recognition, speaker verification, or image retrieval where distinguishing between very similar categories is crucial.
Not ideal if your primary goal is a simple multi-class classification problem where inter-class separation isn't a critical performance bottleneck.
Stars
9
Forks
3
Language
Python
License
—
Category
Last pushed
Apr 17, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/dalisson/am_softmax"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MilaNLProc/contextualized-topic-models
A python package to run contextualized topic modeling. CTMs combine contextualized embeddings...
vinid/cade
Compass-aligned Distributional Embeddings. Align embeddings from different corpora
spcl/ncc
Neural Code Comprehension: A Learnable Representation of Code Semantics
criteo-research/CausE
Code for the Recsys 2018 paper entitled Causal Embeddings for Recommandation.
vintasoftware/entity-embed
PyTorch library for transforming entities like companies, products, etc. into vectors to support...