The tste.py script generally expects an input file of . Each line in your data should represent one "A is closer to B than to C" relationship. 1. Format Your Input
This is commonly used in human perception studies (e.g., taste, art style) where it's easier for humans to rank similarities than to give exact scores. 🛠️ Setup & Installation
python tste.py --triplets triplets.txt --n_objects 100 --n_dims 2 Use code with caution. Copied to clipboard 3. Key Parameters to Tune tste.py
You can typically execute it via terminal. Parameters often include the number of dimensions (usually 2 or 3) and the number of objects:
Most versions of this script on GitHub (like the gcr/tste-theano repository ) are built using older libraries. : You usually need numpy and theano . The tste
Note : Theano is largely discontinued; you may need to use a newer fork like PyTensor or find a Cython-optimized version . : pip install numpy theano Use code with caution. Copied to clipboard 📝 How to Use the Script
: If the embedding looks like a random "ball," try lowering the learning rate. 📊 When to use t-STE vs. t-SNE Learning to Taste A Multimodal Wine Dataset Format Your Input This is commonly used in
(Alpha) : Degrees of freedom for the Student-t distribution (usually set to is dimensions).