SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

loading saved model when n_classes != 2

Browse Source 
Required to for: Assertion `t >= 0 && t < n_classes` failed,  if your default number of classes is not 2.
This commit is contained in:
Jasdeep Singh
2018-12-20 13:55:47 -08:00
committed by GitHub
parent 8da280ebbe
commit 99709ee61d
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/run_classifier.py
View File

@@ -558,7 +558,7 @@ def main():
# Load a trained model that you have fine-tuned
model_state_dict = torch.load(output_model_file)
model = BertForSequenceClassification.from_pretrained(args.bert_model, state_dict=model_state_dict)
model = BertForSequenceClassification.from_pretrained(args.bert_model, state_dict=model_state_dict, num_labels=num_labels)
model.to(device)
if args.do_eval and (args.local_rank == -1 or torch.distributed.get_rank() == 0):