Kemal Kurniawan

I have an issue when compiling your sample code using g++ 4.7.3. Please update the code so it can be compiled with the latest version of g++. Just for information,...

Hi, thanks for the library! Very useful for working with sacred experiments. Is there a way to specify multiple reducers for projection? Say, I want to get the min and...

Rnd changed with a new captured function

2

Versions: - Python 3.7.7 - Sacred 0.8.1 It's easier to explain with an example. So let's say you have this: ```python # main.py from sacred import Experiment ex = Experiment()...

Bias not used

3

Hi, it seems this bias weight in `PairwiseBilinear` is not used. Possibly a (minor) bug? https://github.com/stanfordnlp/stanza/blob/1c73418b65905b2d32f7b0dcb0bdd4a615b6ab0a/stanza/models/common/biaffine.py#L17

Support for newer ACL link format

5

Newer ACL formats are like https://www.aclweb.org/anthology/2020.acl-main.214.pdf which doesn't match the regex rule. ACL links are rather easy as you only need to strip the `.pdf` at the end to get...

Hi, in the line below, it seems that function tags separated with = doesn't get removed from the children's label. That is, when the child has label `NP=2`, this will...

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...