treelstm.pytorch
treelstm.pytorch copied to clipboard
dasguptar
Tree LSTM implementation in PyTorch
Ubuntu 18.04 Java 11.0.3 running (as part of fetch_and_preprocess.sh) `javac -cp $CLASSPATH lib/*.java -Xlint:unchecked` ``` lib/CollapseUnaryTransformer.java:17: error: error while writing CollapseUnaryTransform er: /home/eduard_ergenzinger/treelstm.pytorch/lib/CollapseUnaryTransformer.class public class CollapseUnaryTransformer implements TreeTransformer { ^...
https://github.com/dasguptar/treelstm.pytorch/blob/228a314add09fc7f39ea752aa7b1fcf756cfe277/treelstm/dataset.py#L63
``` tree.state = self.node_forward(inputs[tree.idx], child_c, child_h) ``` len(inputs) == 54 tree.idx == 54 https://github.com/dasguptar/treelstm.pytorch/blob/228a314add09fc7f39ea752aa7b1fcf756cfe277/treelstm/dataset.py#L70 ``` more informations inputs[tree.idx] tensor([[ 3.7410e-02, 5.7619e-02, 3.3822e-01, ..., -3.5774e-02, -7.8579e-02, 1.0644e-02], [-2.5287e-02, -2.5835e-01, -7.5715e-02, ...,...
I have downloaded the SICK data and obtained the dependency and constituency parsing with the fetch_and_preprocess.sh file. I am now trying to understand what is the information that is generated...
I got the same result as you, `~0.846` Pearson score. After checking the original implementation, I found two differences. * In your *trainer.py* file, ```{python} def train(self, dataset): self.model.train() self.optimizer.zero_grad()...
Hello, not an issue, but what's the easiest way to extract the learned hidden embeddings for each node in a ChildSum tree? New to PyTorch, so forgive my ignorance. Thanks!
Existing implementation doesn't support forward/backward with batch of trees as inputs, which is slow in training and inference. The pull requests support batch operation for TreeLSTM, and reproduces the *exact*...
It seems batch size is still not supported from the code? In the forward function of ChildSumTreeLSTM, it seems that it only support process a single tree in one forward....
OS: macOS Mojave Docker Edition: Version 18.03.1-ce-mac65 (24312) Channel: stable I tried to build the docker image in order to run the lib without being dependent on my mac setup....
