Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

onnxruntime support gpu #10668

Merged
merged 15 commits into from
Aug 17, 2023
Merged

onnxruntime support gpu #10668

Changes from all commits
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
c37e36d
Update ch_PP-OCRv3_rec.yml
WenmuZhou Jul 27, 2023
15def6f
Update ch_PP-OCRv3_rec_distillation.yml
WenmuZhou Jul 27, 2023
e6ce08a
Update en_PP-OCRv3_rec.yml
WenmuZhou Jul 27, 2023
8eef9ae
Update arabic_PP-OCRv3_rec.yml
WenmuZhou Jul 27, 2023
264881a
Update chinese_cht_PP-OCRv3_rec.yml
WenmuZhou Jul 27, 2023
5abad67
Update cyrillic_PP-OCRv3_rec.yml
WenmuZhou Jul 27, 2023
7ae68df
Update devanagari_PP-OCRv3_rec.yml
WenmuZhou Jul 27, 2023
4409778
Update japan_PP-OCRv3_rec.yml
WenmuZhou Jul 27, 2023
8343716
Update ka_PP-OCRv3_rec.yml
WenmuZhou Jul 27, 2023
d53a04c
Update korean_PP-OCRv3_rec.yml
WenmuZhou Jul 27, 2023
46f22e0
Update latin_PP-OCRv3_rec.yml
WenmuZhou Jul 27, 2023
335b18d
Update ta_PP-OCRv3_rec.yml
WenmuZhou Jul 27, 2023
5b2829a
Update te_PP-OCRv3_rec.yml
WenmuZhou Jul 27, 2023
11b30e2
Update utility.py
WenmuZhou Aug 17, 2023
f9312f7
Merge branch 'PaddlePaddle:dygraph' into dygraph
WenmuZhou Aug 17, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion tools/infer/utility.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -187,7 +187,10 @@ def create_predictor(args, mode, logger):
if not os.path.exists(model_file_path):
raise ValueError("not find model file path {}".format(
model_file_path))
sess = ort.InferenceSession(model_file_path)
if args.use_gpu:
sess = ort.InferenceSession(model_file_path, providers=['CUDAExecutionProvider'])
else:
sess = ort.InferenceSession(model_file_path)
return sess, sess.get_inputs()[0], None, None

else:
Expand Down