There isn't much new stuff in this release:
- PyTorch 0.4.1 support
- Batched Viterbi decoding (thanks @JeppeHallgren)
Unclaimed project
Are you a maintainer of pytorch-crf? Claim this project to take control of your public changelog and roadmap.
Changelog
(Linear-chain) Conditional random field in PyTorch.
Last updated almost 2 years ago
There isn't much new stuff in this release:
We are now in beta version. Hopefully there won't be anymore breaking changes. Here are the details of what's new:
summed keyword argument in forward method is now removed. Keyword argument of reduce is preferred to match PyTorch's convention.LongTensor before summation to avoid overflow. This is a serious bug for a long in...This just introduces the same changes as version 0.4.1, namely fixing issues #1 and #2, and some refactorings. This backporting is done because some still use PyTorch 0.2 so they can't upgrade to 0.4.1 yet.
__init__ (fixes #1)summed in favor of reduce (fixes #2)PyTorch 0.3.0 is out! We upgrade our PyTorch dependency to version 0.3.0, so now we can use its fancy indexing to get transition score instead of manually broadcasting tensors.
mask to get length by first converting it to LongTensor to avoid overflow.dim explicitly when squeeze-ing to prevent squeezing unintended dime...AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
Stable Diffusion web UI
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
A feature-rich command-line audio/video downloader