FewRel icon indicating copy to clipboard operation
FewRel copied to clipboard

How to run the demo code?

Open CopyNinja1999 opened this issue 2 years ago • 1 comments

Hi, I've downloaded the code and pretrained file as instructed in my Win10 system. My files under the path looks like: data/ LICENSE pair-bert-train_wiki-val_wiki-5-1.pth.tar pretrain/ readme.md fewshot_re_kit/ models/ paper/ pretrain.tar train_demo.py But when I am running the given demo command, it gives me such error: `$ python train_demo.py --trainN 5 --N 5 --K 1 --Q 1 --model pair --encoder bert --pair --hidden_size 768 --val_step 1000 --batch_size 4 --fp16 5-way-1-shot Few-Shot Relation Classification model: pair encoder: bert max_length: 128 Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertForSequenceClassification: ['cls.predictions.transform.dense.weight', 'cls.seq_relationship.bias', 'cls.predictions.bias', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.decoder.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.seq_relationship.weight']

  • This IS expected if you are initializing BertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
  • This IS NOT expected if you are initializing BertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). Some weights of BertForSequenceClassification were not initialized from the model checkpoint at bert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.weight'] You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. [ERROR] Data file does not exist! Traceback (most recent call last): File "C:\Users\RickZZ\OneDrive - University of Southampton\Msc project\FewRel\train_demo.py", line 253, in main() File "C:\Users\RickZZ\OneDrive - University of Southampton\Msc project\FewRel\train_demo.py", line 159, in main test_data_loader = get_loader_pair(opt.test, sentence_encoder, File "C:\Users\RickZZ\OneDrive - University of Southampton\Msc project\FewRel\fewshot_re_kit\data_loader.py", line 226, in get_loader_pair dataset = FewRelDatasetPair(name, encoder, N, K, Q, na_rate, root, encoder_name) File "C:\Users\RickZZ\OneDrive - University of Southampton\Msc project\FewRel\fewshot_re_kit\data_loader.py", line 125, in init assert(0) AssertionError` What should I do to avoid the error?

CopyNinja1999 avatar Mar 20 '22 13:03 CopyNinja1999

Use vals instead of tests: copy val_.json to test_.json

lrongzheni avatar Jul 21 '22 01:07 lrongzheni