torch-simivec

torch-simivec : Multi-label Embedding Training as Similarity Learning Problem

Train an input multi-label embedding as a similarity learning problem.

Usage

Modelling

from torch_simivec import SimiLoss
import torch
import numpy as np

# init the model
model = SimiLoss(
    tokenlist_size=10,
    embedding_size=256,
    context_size=4
)

# create a positive & negative example
X_pos = torch.tensor([[[0, 2, 9], [6, 0, 8], [1, 3, 4], [7, 8, 9]]])
y_pos = torch.tensor([[1, 4, 2]])
np.random.seed(42)
X_neg = torch.tensor(np.random.permutation(X_pos))
y_neg = torch.tensor(np.random.permutation(y_pos))

# compute loss
loss = model(y_pos, X_pos, y_neg, X_neg)
print(loss)

Training

optimizer = torch.optim.Adam(model.parameters(), lr=3e-4)
avg_loss = .0
for epoch in range(50):
    optimizer.zero_grad()
    loss = model(y_pos, X_pos, y_neg, X_neg)
    loss.backward()
    optimizer.step()
    avg_loss += loss.item()
    if (epoch % 10) == 9:
        print(f"epoch {epoch + 1} | loss: {avg_loss / 10.}")
        avg_loss = .0

Appendix

Installation

The torch-simivec git repo is available as PyPi package

pip install torch-simivec
pip install git+ssh://git@github.com/ulf1/torch-simivec.git

Install a virtual environment

python3 -m venv .venv
source .venv/bin/activate
pip install --upgrade pip
pip install -r requirements.txt --no-cache-dir
pip install -r requirements-dev.txt --no-cache-dir
pip install -r requirements-demo.txt --no-cache-dir

(If your git repo is stored in a folder with whitespaces, then don’t use the subfolder .venv. Use an absolute path without whitespaces.)

Python commands

Jupyter for the examples: jupyter lab
Check syntax: flake8 --ignore=F401 --exclude=$(grep -v '^#' .gitignore | xargs | sed -e 's/ /,/g')
Run Unit Tests: PYTHONPATH=. pytest

Publish

pandoc README.md --from markdown --to rst -s -o README.rst
python setup.py sdist
twine upload -r pypi dist/*

Clean up

find . -type f -name "*.pyc" | xargs rm
find . -type d -name "__pycache__" | xargs rm -r
rm -r .pytest_cache
rm -r .venv

Support

Please open an issue for support.

Contributing

Please contribute using Github Flow. Create a branch, add commits, and open a pull request.

Metadata

Release files for torch-simivec 0.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for torch-simivec 0.2.0
File	Size	Uploaded
torch-simivec-0.2.0.tar.gz	8.8 kB	Apr 13, 2022	Details

Release files / torch-simivec-0.2.0.tar.gz

Download URL	torch-simivec-0.2.0.tar.gz
Size	8.8 kB
Tags	Source
SHA-256 checksum How to use checksums	`fcbfb98a527bbb228db33c62f960492cbbf6f3d48bad7390f4adbbdcde4b70b9`
BLAKE2b-256 checksum How to use checksums	`43b1f7422f0fa67ad74652e4618f0da10f2e2af119923b405172e0f3ebb1b5ec`
Upload date	Apr 13, 2022
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.3.0 pkginfo/1.8.2 requests/2.27.1 setuptools/62.1.0 requests-toolbelt/0.9.1 tqdm/4.64.0 CPython/3.7.9`