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

Merge pull request #159 from jaderabbit/master

Browse Source 
Allow do_eval to be used without do_train and to use the pretrained model in the output folder
This commit is contained in:
Thomas Wolf
2019-01-07 12:31:06 +01:00
committed by GitHub
parent 77966a43a4 193e2df8ba
commit 766c6b2ce3
1 changed files with 9 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
examples/run_classifier.py
View File

@@ -432,7 +432,7 @@ def main():
if not args.do_train and not args.do_eval:
raise ValueError("At least one of `do_train` or `do_eval` must be True.")
if os.path.exists(args.output_dir) and os.listdir(args.output_dir):
if os.path.exists(args.output_dir) and os.listdir(args.output_dir) and args.do_train:
raise ValueError("Output directory ({}) already exists and is not empty.".format(args.output_dir))
os.makedirs(args.output_dir, exist_ok=True)
@@ -504,6 +504,8 @@ def main():
t_total=t_total)
global_step = 0
nb_tr_steps = 0
tr_loss = 0
if args.do_train:
train_features = convert_examples_to_features(
train_examples, label_list, args.max_seq_length, tokenizer)
@@ -555,6 +557,7 @@ def main():
# Save a trained model
model_to_save = model.module if hasattr(model, 'module') else model # Only save the model it-self
output_model_file = os.path.join(args.output_dir, "pytorch_model.bin")
if args.do_train:
torch.save(model_to_save.state_dict(), output_model_file)
# Load a trained model that you have fine-tuned
@@ -581,7 +584,8 @@ def main():
model.eval()
eval_loss, eval_accuracy = 0, 0
nb_eval_steps, nb_eval_examples = 0, 0
for input_ids, input_mask, segment_ids, label_ids in eval_dataloader:
for input_ids, input_mask, segment_ids, label_ids in tqdm(eval_dataloader, desc="Evaluating"):
input_ids = input_ids.to(device)
input_mask = input_mask.to(device)
segment_ids = segment_ids.to(device)
@@ -603,11 +607,11 @@ def main():
eval_loss = eval_loss / nb_eval_steps
eval_accuracy = eval_accuracy / nb_eval_examples
loss = tr_loss/nb_tr_steps if args.do_train else None
result = {'eval_loss': eval_loss,
'eval_accuracy': eval_accuracy,
'global_step': global_step,
'loss': tr_loss/nb_tr_steps}
'loss': loss}
output_eval_file = os.path.join(args.output_dir, "eval_results.txt")
with open(output_eval_file, "w") as writer: