Run prediction script on TPU

[ncg-task]

Dear authors,

When we do the following:

!python run_classifier.py --task_name=semeval --do_train=false --do_eval=false --do_predict=true --data_dir=<data-dir> --vocab_file=$BUCKET_NAME/BERT-large-cased/vocab.txt --bert_config_file=$BUCKET_NAME/BERT-large-cased/bert_config.json --init_checkpoint=$BUCKET_NAME/BERT-large-cased/bert_model.ckpt --max_seq_length=128 --predict_batch_size=16 --max_num_relations=12 --do_lower_case=False --use_tpu=True --tpu_name=<address> --output_dir=$OUTPUT_DIR

the following error is displayed

 File "run_classifier.py", line 424, in convert_single_example
    is_real_example=False)
TypeError: __init__() got an unexpected keyword argument 'is_real_example'

My guess is the fix would need to be applied at Line 424? Then the InputFeatures class (Line 178) initialization would work.

Could you kindly provide the list of arguments we would need to supply in order to enable the function? Or at least some direction to resolve the error to run the prediction script on TPU would be most appreciated.

Thank you very much.

[helloeve]

Thank you for your interests on our work! In our work we were not using TPU for experiments, so all the branches that are related to TPU was not updated. My best suggestion to make it work is to make sure PaddingInputExample to accept the same parameters as InputExample, which is what we used for GPU version.

[ncg-task]

Hello, thank you very much for your reply! And thank you for the very relevant advice. May I please ask in which class would we find the implementation for PaddingInputExample so that we can modify it? I will be happy to share the code update in case I manage to get to work.