pytorch-struct

pytorch-struct copied to clipboard

Alignment CRF error

6

Looks like there is an error now on install for AlignmentCRF. https://github.com/harvardnlp/pytorch-struct/blob/master/notebooks/CTC_with_padding.ipynb ``` Find marginals (see uncertainty from randomness) show(dist.marginals, 1) ``` Error: ` ~/opt/anaconda3/lib/python3.7/site-packages/torch_struct/alignment.py in _dp_scan(self, log_potentials, lengths, force_grad)...

jdegange

Conditional and joint span probabilities in TreeCRF

5

I want to use the TreeCRF class to learn latent tree distributions for constituency trees for sentences. I noticed you can easily obtain the text span marginals with `.marginals`. However,...

rubencart

Nonprojective dependency entropy

9

Hi Sasha, Wanted to contribute an efficient implementation of entropy for non-projective trees I'm using for a current project. Please let me know of any changes you'd like to see....

teffland

gumbel crf

1

Hi, Is the [gumbel_crf](https://github.com/harvardnlp/pytorch-struct/blob/master/torch_struct/distributions.py#L187) function ready to use? If so, can you point me to the relevant documentation? (I cannot find it anywhere in [here](http://nlp.seas.harvard.edu/pytorch-struct/)) Thanks!

chijames

Question on the Complexity of CKY

8

1. By using the GPU, we are able to reduce the complexity of linear-chain CRF from O(NT^2) to O(log N). where N is the sentence length and T is the...

allanj

notebooks are broken

7

CTC, CTC_with_padding, and Unsupervised_CFG notebooks are not working. in sparse.py L591 too many values to unpack for CTCs and no module named torch_struct.networks for CFG.

volkancirik

Value expectation and 1st order CKY

4

Changes are: * Add 1st order cky implementation with suggested updates * Add value-expectation semiring and test * Make marginal computation work on potentials w/o gradients * Minor clarity/consistency changes...

teffland

https://arxiv.org/abs/2006.01112

srush

differentiable samples (rsample)

11

Are there plans to introduce differentiable samples? Thanks!

RafaelPo

Increasing memory usage of DependencyCRF

4

Running the piece of code below multiple times (with `CUDA_VISIBLE_DEVICES` is set to a single GPU id) ```python _ = DependencyCRF(torch.zeros(5,5,5).cuda(), multiroot=False).marginals print(torch.cuda.memory_allocated()) ``` will result in increasing allocated CUDA...

kmkurn