uditarora / ood-text-emnlp Goto Github PK

Dear Authors,
A huge thanks for outsourcing your code, your very clear poster presentation, and answering the question during the conference :) . This is a great paper and very valuable code.
Cheers,
Pierre

Hi,

I was trying to run the model for mnli in distribution and snli out of distribution dataset using the following command (The mnli model is already pretained)

id_data="mnli"
ood_data="snli"
python3 msp_eval.py --model_path roberta_ckpts/roberta-$id_data --dataset_name $ood_data --fname ${id_data}_$ood_data --batch_size 8 

However as snli has -1 class label showing the following error in criterion function which is nn.CrossEntropyLoss()

The error message is:

cunn_ClassNLLCriterion_updateOutput_kernel: block: [0,0,0], thread: [2,0,0] Assertion t >= 0 && t < n_classes failed.

How to solve the problem? Any suggestions? Thanks in advance.