search

declare-lab / ASTE-RL

This repository contains the source codes for the paper: "Aspect Sentiment Triplet Extraction using Reinforcement Learning" published at CIKM 2021.
Apache License 2.0
18 stars 3 forks source link

Using own data #1

Open ajaysurya1221 opened 2 years ago

ajaysurya1221 commented 2 years ago

Loading data... {'NEU': 2442, 'POS': 738, 'NEG': 1390} ['NEU', 'POS', 'NEG']

train_data: 2277

dev_data: 587

test_data: 777

Starting training service, overall process number: 1 Train epoch 0 ... Process 0 start service. Train batch 0 : F1= 0.9047619047619047 , time= 6.834511995315552 Train batch 50 : F1= 0.9473684210526316 , time= 5.462005853652954 Process Process-2: Traceback (most recent call last): File "/usr/lib/python3.7/multiprocessing/process.py", line 297, in _bootstrap self.run() File "/usr/lib/python3.7/multiprocessing/process.py", line 99, in run self._target(*self._args, *self._kwargs) File "/content/ASTE-RL/TrainProcess.py", line 138, in worker acc, cnt, tot, loss = workProcess(model, datas, sample_round, mode, device, sentiments, test) File "/content/ASTE-RL/TrainProcess.py", line 25, in workProcess preoptions, pre_aspect_actions, pre_opinion_actions, device, sentiments) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(input, **kwargs) File "/content/ASTE-RL/Model.py", line 156, in forward posvs[y], bot_bert_cls, self.opinionvector(actionb), wordinbot[y], \ IndexError: index 96 is out of bounds for dimension 0 with size 96

Please Help.

Jurys22 commented 2 years ago

I have not used this repo yet, just going to use it soon. From the error it seems an out of bound of the data - word vector it is processing.

Jurys22 commented 2 years ago

Question: how fast for it was going from the start to process Process 2?